Author name cluster

Lerrel Pinto

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

50 papers

2 author rows

ICRA Conference 2025 Conference Paper

AnySkin: Plug-and-Play Skin Sensing for Robotic Touch

Raunaq M. Bhirangi
Venkatesh Pattabiraman
Enes Erciyes
Yifeng Cao
Tess Lee Hellebrekers
Lerrel Pinto

While tactile sensing is widely accepted as an important and useful sensing modality, its use pales in comparison to other sensory modalities like vision and proprioception. AnySkin addresses the critical challenges that impede the use of tactile sensing - versatility, replaceability, and data reusability. Building on the simplistic design of ReSkin, and decoupling the sensing electronics from the sensing interface, AnySkin simplifies integration making it as straightforward as putting on a phone case and connecting a charger. Furthermore, AnySkin is the first uncalibrated tactile-sensor to report crossinstance generalizability of learned manipulation policies. To summarize, this work makes three key contributions: first, we introduce a streamlined fabrication process and a design tool for creating an adhesive-free, durable and easily replaceable magnetic tactile sensor; second, we characterize slip detection and policy learning with the AnySkin sensor; third, we demonstrate zero-shot generalization of models trained on one instance of AnySkin to new instances, and compare it with popular existing tactile solutions like DIGIT and ReSkin. Code, design files, and videos of policy experiments can be found on https://any-skin.github.io

ICLR Conference 2025 Conference Paper

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Davide Paglieri
Bartlomiej Cupial
Samuel Coward
Ulyana Piterbarg
Maciej Wolczyk
Akbir Khan
Eduardo Pignatelli
Lukasz Kucinski

Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well in complex, dynamic environments. Real-world tasks require handling intricate interactions, advanced spatial reasoning, long-term planning, and continuous exploration of new strategies—areas in which we lack effective methodologies for comprehensively evaluating these capabilities. To address this gap, we introduce BALROG, a novel benchmark designed to assess the agentic capabilities of LLMs and VLMs through a diverse set of challenging games. Our benchmark incorporates a range of existing reinforcement learning environments with varying levels of difficulty, including tasks that are solvable by non-expert humans in seconds to extremely challenging ones that may take years to master (e.g., the NetHack Learning Environment). We devise fine-grained metrics to measure performance and conduct an extensive evaluation of several popular open-source and closed-source LLMs and VLMs. Our findings indicate that while current models achieve partial success in the easier games, they struggle significantly with more challenging tasks. Notably, we observe severe deficiencies in vision-based decision-making, as several models perform worse when visual representations of the environments are provided. We release BALROG as an open and user-friendly benchmark to facilitate future research and development in the agentic community. Code and Leaderboard at balrogai.com

ICRA Conference 2025 Conference Paper

Bridging the Human to Robot Dexterity Gap Through Object-Oriented Rewards

Irmak Güzey
Yinlong Dai
Georgy Savva
Raunaq M. Bhirangi
Lerrel Pinto

Training robots directly from human videos is an emerging area in robotics and computer vision. While there has been notable progress with two-fingered grippers, learning autonomous tasks without teleoperation remains a difficult problem for multi-fingered robot hands. A key reason for this difficulty is that a policy trained on human hands may not directly transfer to a robot hand with a different morphology. In this work, we present HUDOR, a technique that enables online fine-tuning of the policy by constructing a reward function from the human video. Importantly, this reward function is built using object-oriented rewards derived from off-the-shelf point trackers, which allows for meaningful learning signals even when the robot hand is in the visual observation, while the human hand is used to construct the reward. Given a single video of human solving a task, such as gently opening a music box, HUDOR allows our four-fingered Allegro hand to learn this task with just an hour of online interaction. Our experiments across four tasks, show that HUDOR outperforms alternatives with an average of $4 \times$ improvement. Code and videos are available on our website https://object-rewards.github.io/.

ICML Conference 2025 Conference Paper

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Gaoyue Zhou
Hengkai Pan
Yann LeCun
Lerrel Pinto

The ability to predict future outcomes given control actions is fundamental for physical reasoning. However, such predictive models, often called world models, remain challenging to learn and are typically developed for task-specific solutions with online policy learning. To unlock world models’ true potential, we argue that they should 1) be trainable on offline, pre-collected trajectories, 2) support test-time behavior optimization, and 3) facilitate task-agnostic reasoning. To this end, we present DINO World Model (DINO-WM), a new method to model visual dynamics without reconstructing the visual world. DINO-WM leverages spatial patch features pre-trained with DINOv2, enabling it to learn from offline behavioral trajectories by predicting future patch features. This allows DINO-WM to achieve observational goals through action sequence optimization, facilitating task-agnostic planning by treating goal features as prediction targets. We demonstrate that DINO-WM achieves zero-shot behavioral solutions at test time on six environments without expert demonstrations, reward modeling, or pre-learned inverse models, outperforming prior state-of-the-art work across diverse task families such as arbitrarily configured mazes, push manipulation with varied object shapes, and multi-particle scenarios.

ICRA Conference 2025 Conference Paper

Dynamem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation

Peiqi Liu
Zhanqiu Guo
Mohit Warke
Soumith Chintala
Chris Paxton 0001
Nur Muhammad (Mahi) Shafiullah
Lerrel Pinto

Significant progress has been made in openvocabulary mobile manipulation, where the goal is for a robot to perform tasks in any environment given a natural language description. However, most current systems assume a static environment, which limits the system's applicability in realworld scenarios where environments frequently change due to human intervention or the robot's own actions. In this work, we present DynaMem, a new approach to open-world mobile manipulation that uses a dynamic spatio-semantic memory to represent a robot's environment. DynaMem constructs a 3D data structure to maintain a dynamic memory of point clouds, and answers open-vocabulary object localization queries using multimodal LLMs or open-vocabulary features generated by state-of-the-art vision-language models. Powered by DynaMem, our robots can explore novel environments, search for objects not found in memory, and continuously update the memory as objects move, appear, or disappear in the scene. We run extensive experiments on the Stretch SE3 robots in three real and nine offline scenes, and achieve an average pick-and-drop success rate of 70 % on non-stationary objects, which is more than a $\mathbf{2} \times$ improvement over state-of-the-art static systems.

ICRA Conference 2025 Conference Paper

P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policies

Mara Levy
Siddhant Haldar
Lerrel Pinto
Abhinav Shirivastava

Developing generalizable robot policies that can robustly handle varied environmental conditions and object instances remains a fundamental challenge in robot learning. While considerable efforts have focused on collecting large robot datasets and developing policy architectures to learn from such data, naïvely learning from visual inputs often results in brittle policies that fail to transfer beyond the training data. This work presents Prescriptive Point Priors for Policies or P3-PO, a novel framework that constructs a unique state representation of the environment leveraging recent advances in computer vision and robot learning to achieve improved out-of-distribution generalization for robot manipulation. This representation is obtained through two steps. First, a human annotator prescribes a set of semantically meaningful points on a single demonstration frame. These points are then propagated through the dataset using off-the-shelf vision models. The derived points serve as an input to state-of-the-art policy architectures for policy learning. Our experiments across four real-world tasks demonstrate an overall 43% absolute improvement over prior methods when evaluated in identical settings as training. Further, P3-PO exhibits 58% and 80% gains across tasks for new object instances and more cluttered environments respectively. Videos illustrating the robot's performance are best viewed at point-priors.github.io.

ICRA Conference 2025 Conference Paper

Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments

Haritheja Etukuru
Norihito Naka
Zijin Hu
Seungjae Lee 0001
Julian Mehu
Aaron Edsinger
Chris Paxton 0001
Soumith Chintala

Robot models, particularly those trained with large amounts of data, have recently shown a plethora of real-world manipulation and navigation capabilities. Several independent efforts have shown that given sufficient training data in an environment, robot policies can generalize to demonstrated variations in that environment. However, needing to finetune robot models to every new environment stands in stark contrast to models in language or vision that can be deployed zero-shot for open-world problems. In this work, we present Robot Utility Models (RUMs), a framework for training and deploying zero-shot robot policies that can directly generalize to new environments without any finetuning. To create RUMs efficiently, we develop new tools to quickly collect data for mobile manipulation tasks, integrate such data into a policy with multi-modal imitation learning, and deploy policies ondevice on the Hello Robot Stretch, a cheap commodity robot, with an external mLLM verifier for retrying. We train five such utility models for opening cabinet doors, opening drawers, picking up napkins, picking up paper bags, and reorienting fallen objects. Our system, on average, achieves 90% success rate in unseen, novel environments interacting with unseen objects. Primary among our lessons are the importance of training data over training algorithm and policy class, guidance about data scaling, necessity for diverse yet high-quality demonstrations, and a recipe for robot introspection and retrying to improve performance on individual environments.

ICLR Conference 2025 Conference Paper

Training Language Models on Synthetic Edit Sequences Improves Code Synthesis

Ulyana Piterbarg
Lerrel Pinto
Rob Fergus

Software engineers mainly write code by editing existing programs. In contrast, language models (LMs) autoregressively synthesize programs in a single pass. One explanation for this is the scarcity of sequential edit data. While high-quality instruction data for code synthesis is scarce, edit data for synthesis is even scarcer. To fill this gap, we develop a synthetic data generation algorithm called LintSeq. This algorithm refactors programs into sequences of synthetic edits by using a linter to procedurally sample across interdependent lines of source code. Synthetic edits sampled with LintSeq reflect the syntax and semantics of their programming language. To test the algorithm, we use it to refactor a dataset of instruction + program pairs into instruction + program-diff-sequence tuples. Then, we fine-tune a series of smaller LMs ranging from 2.6B to 14B parameters on both the re-factored and original versions of this dataset. We perform comprehensive evaluations comparing edit sequence code LMs against baselines on HumanEval, MBPP(+), CodeContests, DS-1000, and BigCodeBench. We show that models fine-tuned to iteratively synthesize code match or outperform baselines on pass@1, and exhibit better scaling across higher pass@k as a function of total test-time FLOPs. Finally, we also pretrain our own tiny LMs for code understanding. We show that fine-tuning these models to synthesize code edit-by-edit results in strong performance on HumanEval and MBPP(+) compared to existing code language models of similar scale such as CodeT5+, AlphaCode, and Codex.

ICML Conference 2024 Conference Paper

Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction

Chen-Yu Yen
Raghav Singhal
Umang Sharma
Rajesh Ranganath
Sumit Chopra
Lerrel Pinto

Magnetic Resonance (MR) imaging, despite its proven diagnostic utility, remains an inaccessible imaging modality for disease surveillance at the population level. A major factor rendering MR inaccessible is lengthy scan times. An MR scanner collects measurements associated with the underlying anatomy in the Fourier space, also known as the k-space. Creating a high-fidelity image requires collecting large quantities of such measurements, increasing the scan time. Traditionally to accelerate an MR scan, image reconstruction from under-sampled k-space data is the method of choice. However, recent works show the feasibility of bypassing image reconstruction and directly learning to detect disease directly from a sparser learned subset of the k-space measurements. In this work, we propose Adaptive Sampling for MR (ASMR), a sampling method that learns an adaptive policy to sequentially select k-space samples to optimize for target disease detection. On 6 out of 8 pathology classification tasks spanning the Knee, Brain, and Prostate MR scans, ASMR reaches within 2% of the performance of a fully sampled classifier while using only 8% of the k-space, as well as outperforming prior state-of-the-art work in k-space sampling such as EMRT, LOUPE, and DPS.

NeurIPS Conference 2024 Conference Paper

BAKU: An Efficient Transformer for Multi-Task Policy Learning

Siddhant Haldar
Zhuoran Peng
Lerrel Pinto

Training generalist agents capable of solving diverse tasks is challenging, often requiring large datasets of expert demonstrations. This is particularly problematic in robotics, where each data point requires physical execution of actions in the real world. Thus, there is a pressing need for architectures that can effectively leverage the available training data. In this work, we present BAKU, a simple transformer architecture that enables efficient learning of multi-task robot policies. BAKU builds upon recent advancements in offline imitation learning and meticulously combines observation trunks, action chunking, multi-sensory observations, and action heads to substantially improve upon prior work. Our experiments on 129 simulated tasks across LIBERO, Meta-World suite, and the Deepmind Control suite exhibit an overall 18% absolute improvement over RT-1 and MT-ACT, with a 36% improvement on the harder LIBERO benchmark. On 30 real-world manipulation tasks, given an average of just 17 demonstrations per task, BAKU achieves a 91% success rate. Videos of the robot are best viewed at baku-robot. github. io.

PDF Details DOI

ICML Conference 2024 Conference Paper

Behavior Generation with Latent Actions

Seungjae Lee 0001
Yibin Wang 0008
Haritheja Etukuru
H. Jin Kim
Nur Muhammad (Mahi) Shafiullah
Lerrel Pinto

Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision-making. Unlike language or image generation, decision-making requires modeling actions – continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction. A recent class of models called Behavior Transformers (BeT) addresses this by discretizing actions using k-means clustering to capture different modes. However, k-means struggles to scale for high-dimensional action spaces or long sequences, and lacks gradient information, and thus BeT suffers in modeling long-range actions. In this work, we present Vector-Quantized Behavior Transformer (VQ-BeT), a versatile model for behavior generation that handles multimodal action prediction, conditional generation, and partial observations. VQ-BeT augments BeT by tokenizing continuous actions with a hierarchical vector quantization module. Across seven environments including simulated manipulation, autonomous driving, and robotics, VQ-BeT improves on state-of-the-art models such as BeT and Diffusion Policies. Importantly, we demonstrate VQ-BeT’s improved ability to capture behavior modes while accelerating inference speed 5× over Diffusion Policies. Videos can be found https: //sjlee. cc/vq-bet/

ICML Conference 2024 Conference Paper

diff History for Neural Language Agents

Ulyana Piterbarg
Lerrel Pinto
Rob Fergus

Neural Language Models (LMs) offer an exciting solution for general-purpose embodied control. However, a key technical issue arises when using an LM-based controller: environment observations must be converted to text, which coupled with history, results in long and verbose textual prompts. As a result, prior work in LM agents is limited to restricted domains with small observation size as well as minimal needs for interaction history or instruction finetuning. In this paper, we introduce diff history, a simple and highly effective solution to these issues. By applying the Unix diff command on consecutive text observations in the interaction histories used to prompt LM policies, we can both abstract away redundant information and focus the content of textual inputs on the salient changes in the environment. On NetHack, an unsolved video game that requires long-horizon reasoning for decision-making, LMs tuned with diff history match state-of-the-art performance for neural agents while needing 1800X fewer training examples compared to prior work. Even on the simpler BabyAI-Text environment with concise text observations, we find that although diff history increases the length of prompts, the representation it provides offers a 25% improvement in the efficiency of low-sample instruction finetuning. Further, we show that diff history scales favorably across different finetuning dataset sizes. We open-source our code and data to https: //diffhistory. github. io.

NeurIPS Conference 2024 Conference Paper

DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control

Zichen J. Cui
Hengkai Pan
Aadhithya Iyer
Siddhant Haldar
Lerrel Pinto

Imitation learning has proven to be a powerful tool for training complex visuo-motor policies. However, current methods often require hundreds to thousands of expert demonstrations to handle high-dimensional visual observations. A key reason for this poor data efficiency is that visual representations are predominantly either pretrained on out-of-domain data or trained directly through a behavior cloning objective. In this work, we present DynaMo, a new in-domain, self-supervised method for learning visual representations. Given a set of expert demonstrations, we jointly learn a latent inverse dynamics model and a forward dynamics model over a sequence of image embeddings, predicting the next frame in latent space, without augmentations, contrastive sampling, or access to ground truth actions. Importantly, DynaMo does not require any out-of-domain data such as Internet datasets or cross-embodied datasets. On a suite of six simulated and real environments, we show that representations learned with DynaMo significantly improve downstream imitation learning performance over prior self-supervised learning objectives, and pretrained representations. Gains from using DynaMo hold across policy classes such as Behavior Transformer, Diffusion Policy, MLP, and nearest neighbors. Finally, we ablate over key components of DynaMo and measure its impact on downstream policy performance. Robot videos are best viewed at https: //dynamo-ssl. github. io.

PDF Details DOI

ICML Conference 2024 Conference Paper

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling

Raunaq M. Bhirangi
Chenyu Wang
Venkatesh Pattabiraman
Carmel Majidi
Abhinav Gupta 0001
Tess Lee Hellebrekers
Lerrel Pinto

Reasoning from sequences of raw sensory data is a ubiquitous problem across fields ranging from medical devices to robotics. These problems often involve using long sequences of raw sensor data (e. g. magnetometers, piezoresistors) to predict sequences of desirable physical quantities (e. g. force, inertial measurements). While classical approaches are powerful for locally-linear prediction problems, they often fall short when using real-world sensors. These sensors are typically non-linear, are affected by extraneous variables (e. g. vibration), and exhibit data-dependent drift. For many problems, the prediction task is exacerbated by small labeled datasets since obtaining ground-truth labels requires expensive equipment. In this work, we present Hierarchical State-Space models (HiSS), a conceptually simple, new technique for continuous sequential prediction. HiSS stacks structured state-space models on top of each other to create a temporal hierarchy. Across six real-world sensor datasets, from tactile-based state prediction to accelerometer-based inertial measurement, HiSS outperforms state-of-the-art sequence models such as causal Transformers, LSTMs, S4, and Mamba by at least 23% on MSE. Our experiments further indicate that HiSS demonstrates efficient scaling to smaller datasets and is compatible with existing data-filtering techniques. Code, datasets and videos can be found on https: //hiss-csp. github. io.

ICRA Conference 2024 Conference Paper

Open X-Embodiment: Robotic Learning Datasets and RT-X Models: Open X-Embodiment Collaboration

Abby O'Neill
Abdul Rehman
Abhiram Maddukuri
Abhishek Gupta 0004
Abhishek Padalkar
Abraham Lee
Acorn Pooley
Agrim Gupta

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x. github.io.

ICRA Conference 2024 Conference Paper

See to Touch: Learning Tactile Dexterity through Visual Incentives

Irmak Güzey
Yinlong Dai
Ben Evans
Soumith Chintala
Lerrel Pinto

Equipping multi-fingered robots with tactile sensing is crucial for achieving the precise, contact-rich, and dexterous manipulation that humans excel at. However, relying solely on tactile sensing fails to provide adequate cues for reasoning about objects’ spatial configurations, limiting the ability to correct errors and adapt to changing situations. In this paper, we present Tactile Adaptation from Visual Incentives (TAVI), a new framework that enhances tactile-based dexterity by optimizing dexterous policies using vision-based rewards. First, we use a contrastive-based objective to learn visual representations. Next, we construct a reward function using these visual representations through optimal-transport based matching on one human demonstration. Finally, we use online reinforcement learning on our robot to optimize tactile-based policies that maximize the visual reward. On six challenging tasks, such as peg pick-and-place, unstacking bowls, and flipping slender objects, TAVI achieves a success rate of 73% using our four-fingered Allegro robot hand. The increase in performance is 108% higher than policies using tactile and vision-based rewards and 135% higher than policies without tactile observational input. Robot videos are best viewed on our project website: https://see-to-touch.github.io/.

ICRA Conference 2023 Conference Paper

Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation

Sridhar Pandian Arunachalam
Sneha Silwal
Ben Evans
Lerrel Pinto

Optimizing behaviors for dexterous manipulation has been a longstanding challenge in robotics, with a variety of methods from model-based control to model-free reinforcement learning having been previously explored in literature. Such prior work often require extensive trial-and-error training along with task-specific tuning of reward functions, which makes applying dexterous manipulation for general purpose problems quite impractical. A sample-efficient and practical alternate to trial-and-error learning is imitation learning. However, collecting and learning from demonstrations in dexterous manipulation is quite challenging due to the high-dimensional action-space involved with multi-finger control. In this work, we propose ‘Dexterous Imitation Made Easy’ (DIME) a new imitation learning framework for dexterous manipulation. DIME only requires a single RGB camera that observes a human operator to teleoperate a robotic hand. Once demonstrations are collected, DIME employs state-of-the-art imitation learning methods to train dexterous manipulation policies. On real robot benchmarks we demonstrate that DIME can be used to solve complex, in-hand manipulation tasks such as ‘flipping’, ‘spinning’, and ‘rotating’ objects with just 30 demonstrations and no additional robot training. Our code, pre-collected demonstrations, and robot videos are publicly available at: https://nyu-robot-learning.github.io/dime.

ICLR Conference 2023 Conference Paper

From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data

Zichen Jeff Cui
Yibin Wang 0008
Nur Muhammad (Mahi) Shafiullah
Lerrel Pinto

While large-scale sequence modelling from offline data has led to impressive performance gains in natural language generation and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that uncurated robot demonstration data, i.e. play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal. This makes extracting useful, task-centric behaviors from such data a difficult generative modelling problem. In this work, we present Conditional Behavior Transformers (C-BeT), a method that combines the multi-modal generation ability of Behavior Transformer with future-conditioned goal specification. On a suite of simulated benchmark tasks, we find that C-BeT improves upon prior state-of-the-art work in learning from play data by an average of 45.7%. Further, we demonstrate for the first time that useful task-centric behaviors can be learned on a real-world robot purely from play data without any task labels or reward information. Robot videos are best viewed on our project website: play-to-policy.github.io

ICRA Conference 2023 Conference Paper

Holo-Dex: Teaching Dexterity with Immersive Mixed Reality

Sridhar Pandian Arunachalam
Irmak Güzey
Soumith Chintala
Lerrel Pinto

A fundamental challenge in teaching robots is to provide an effective interface for human teachers to demonstrate useful skills to a robot. This challenge is exacerbated in dexterous manipulation, where teaching high-dimensional, contact-rich behaviors often require esoteric teleoperation tools. In this work, we present Holo − Dex, a framework for dexter-ous manipulation that places a teacher in an immersive mixed reality through commodity VR headsets. The high-fidelity hand pose estimator onboard the headset is used to teleoperate the robot and collect demonstrations for a variety of general-purpose dexterous tasks. Given these demonstrations, we use powerful feature learning combined with non-parametric imi-tation to train dexterous skills. Our experiments on six common dexterous tasks, including in-hand rotation, spinning, and bottle opening, indicate that HOLO-DEX can both collect high-quality demonstration data and train skills in a matter of hours. Finally, we find that our trained skills can exhibit generalization on objects not seen in training. Videos of HOLO − DEX are available on {https://holo-dex.github.io/. }

AAAI Conference 2023 Conference Paper

Improving Long-Horizon Imitation through Instruction Prediction

Joey Hejna
Pieter Abbeel
Lerrel Pinto

Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents. Difficulties in such settings are exacerbated in low data regimes where over-fitting stifles generalization and compounding errors hurt accuracy. In this work, we explore the use of an often unused source of auxiliary supervision: language. Inspired by recent advances in transformer-based models, we train agents with an instruction prediction loss that encourages learning temporally extended representations that operate at a high level of abstraction. Concretely, we demonstrate that instruction modeling significantly improves performance in planning environments when training with a limited number of demonstrations on the BabyAI and Crafter benchmarks. In further analysis we find that instruction modeling is most important for tasks that require complex reasoning, while understandably offering smaller gains in environments that require simple plans. More details and code can be found at \url{https://github.com/jhejna/instruction-prediction}.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Learning Simultaneous Navigation and Construction in Grid Worlds

Wenyu Han
Haoran Wu
Eisuke Hirota
Alexander Gao
Lerrel Pinto
Ludovic Righetti
Chen Feng 0002

We propose to study a new learning task, mobile construction, to enable an agent to build designed structures in 1/2/3D grid worlds while navigating in the same evolving environments. Unlike existing robot learning tasks such as visual navigation and object manipulation, this task is challenging because of the interdependence between accurate localization and strategic construction planning. In pursuit of generic and adaptive solutions to this partially observable Markov decision process (POMDP) based on deep reinforcement learning (RL), we design a Deep Recurrent Q-Network (DRQN) with explicit recurrent position estimation in this dynamic grid world. Our extensive experiments show that pre-training this position estimation module before Q-learning can significantly improve the construction performance measured by the intersection-over-union score, achieving the best results in our benchmark of various baselines including model-free and model-based RL, a handcrafted SLAM-based policy, and human players. Our code is available at: https://ai4ce.github.io/SNAC/.

NeurIPS Conference 2023 Conference Paper

NetHack is Hard to Hack

Ulyana Piterbarg
Lerrel Pinto
Rob Fergus

Neural policy learning methods have achieved remarkable results in various control problems, ranging from Atari games to simulated locomotion. However, these methods struggle in long-horizon tasks, especially in open-ended environments with multi-modal observations, such as the popular dungeon-crawler game, NetHack. Intriguingly, the NeurIPS 2021 NetHack Challenge revealed that symbolic agents outperformed neural approaches by over four times in median game score. In this paper, we delve into the reasons behind this performance gap and present an extensive study on neural policy learning for NetHack. To conduct this study, we analyze the winning symbolic agent, extending its codebase to track internal strategy selection in order to generate one of the largest available demonstration datasets. Utilizing this dataset, we examine (i) the advantages of an action hierarchy; (ii) enhancements in neural architecture; and (iii) the integration of reinforcement learning with imitation learning. Our investigations produce a state-of-the-art neural agent that surpasses previous fully neural policies by 127% in offline settings and 25% in online settings on median game score. However, we also demonstrate that mere scaling is insufficient to bridge the performance gap with the best symbolic models or even the top human players.

ICRA Conference 2023 Conference Paper

Train Offline, Test Online: A Real Robot Learning Benchmark

Gaoyue Zhou
Victoria Dean
Mohan Kumar Srirama
Aravind Rajeswaran
Jyothish Pari
Kyle Beltran Hatch
Aryan Jain
Tianhe Yu

Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do not generalize across labs), and we lack internet-scale robotics data. We take on these challenges via a new benchmark: Train Offline, Test Online (TOTO). TOTO provides remote users with access to shared robots for evaluating methods on common tasks and an open-source dataset of these tasks for offline training. Its manipulation task suite requires challenging generalization to unseen objects, positions, and lighting. We present initial results on TOTO comparing five pretrained visual representations and four offline policy learning baselines, remotely contributed by five institutions. The real promise of TOTO, however, lies in the future: we release the benchmark for additional submissions from any user, enabling easy, direct comparison to several methods without the need to obtain hardware or collect data.

NeurIPS Conference 2022 Conference Paper

Behavior Transformers: Cloning $k$ modes with one stone

Nur Muhammad Shafiullah
Zichen Cui
Ariuntuya (Arty) Altanzaya
Lerrel Pinto

While behavior learning has made impressive progress in recent times, it lags behind computer vision and natural language processing due to its inability to leverage large, human-generated datasets. Human behavior has a wide variance, multiple modes, and human demonstrations naturally do not come with reward labels. These properties limit the applicability of current methods in Offline RL and Behavioral Cloning to learn from large, pre-collected datasets. In this work, we present Behavior Transformer (BeT), a new technique to model unlabeled demonstration data with multiple modes. BeT retrofits standard transformer architectures with action discretization coupled with a multi-task action correction inspired by offset prediction in object detection. This allows us to leverage the multi-modal modeling ability of modern transformers to predict multi-modal continuous actions. We experimentally evaluate BeT on a variety of robotic manipulation and self-driving behavior datasets. We show that BeT significantly improves over prior state-of-the-art work on solving demonstrated tasks while capturing the major modes present in the pre-collected datasets. Finally, through an extensive ablation study, we further analyze the importance of every crucial component in BeT. Videos of behavior generated by BeT are available here: https: //mahis. life/bet

ICRA Conference 2022 Conference Paper

Context is Everything: Implicit Identification for Dynamics Adaptation

Ben Evans
Abitha Thankaraj
Lerrel Pinto

Understanding environment dynamics is necessary for robots to act safely and optimally in the world. In realistic scenarios, dynamics are non-stationary and the causal variables such as environment parameters cannot necessarily be precisely measured or inferred, even during training. We propose Implicit Identification for Dynamics Adaptation (IIDA), a simple method to allow predictive models to adapt to changing environment dynamics. IIDA assumes no access to the true variations in the world and instead implicitly infers properties of the environment from a small amount of contextual data. We demonstrate IIDA's ability to perform well in unseen environments through a suite of simulated experiments on MuJoCo environments and a real robot dynamic sliding task. In general, IIDA significantly reduces model error and results in higher task performance over commonly used methods. Our code, video of the method, and latest paper is available here https://bennevans.github.io/icra-iida/

IROS Conference 2022 Conference Paper

Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation

Albert Zhan
Ruihan Zhao 0001
Lerrel Pinto
Pieter Abbeel
Michael Laskin

Recent advances in unsupervised representation learning significantly improved the sample efficiency of training Reinforcement Learning policies in simulated environments. However, similar gains have not yet been seen for real-robot reinforcement learning. In this work, we focus on enabling data-efficient real-robot learning from pixels. We present Contrastive Pre-training and Data Augmentation for Efficient Robotic Learning (CoDER), a method that utilizes data augmentation and unsupervised learning to achieve sample-efficient training of real-robot arm policies from sparse rewards. While contrastive pre-training, data augmentation, demonstrations, and reinforcement learning are alone insufficient for efficient learning, our main contribution is showing that the combination of these disparate techniques results in a simple yet data-efficient method. We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels, such as reaching, picking, moving, pulling a large object, flipping a switch, and opening a drawer in just 30 minutes of mean real-world training time. We include videos and code on the project website: https://sites.google.com/view/efficient-robotic-manipulation/home.

ICLR Conference 2022 Conference Paper

Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning

Denis Yarats
Rob Fergus
Alessandro Lazaric
Lerrel Pinto

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data augmentation to learn directly from pixels. We introduce several improvements that yield state-of-the-art results on the DeepMind Control Suite. Notably, DrQ-v2 is able to solve complex humanoid locomotion tasks directly from pixel observations, previously unattained by model-free RL. DrQ-v2 is conceptually simple, easy to implement, and provides significantly better computational footprint compared to prior work, with the majority of tasks taking just 8 hours to train on a single GPU. Finally, we publicly release DrQ-v2 's implementation to provide RL practitioners with a strong and computationally efficient baseline.

ICLR Conference 2022 Conference Paper

One After Another: Learning Incremental Skills for a Changing World

Nur Muhammad (Mahi) Shafiullah
Lerrel Pinto

Reward-free, unsupervised discovery of skills is an attractive alternative to the bottleneck of hand-designing rewards in environments where task supervision is scarce or expensive. However, current skill pre-training methods, like many RL techniques, make a fundamental assumption -- stationary environments during training. Traditional methods learn all their skills simultaneously, which makes it difficult for them to both quickly adapt to changes in the environment, and to not forget earlier skills after such adaptation. On the other hand, in an evolving or expanding environment, skill learning must be able to adapt fast to new environment situations while not forgetting previously learned skills. These two conditions make it difficult for classic skill discovery to do well in an evolving environment. In this work, we propose a new framework for skill discovery, where skills are learned one after another in an incremental fashion. This framework allows newly learned skills to adapt to new environment or agent dynamics, while the fixed old skills ensure the agent doesn't forget a learned skill. We demonstrate experimentally that in both evolving and static environments, incremental skills significantly outperform current state-of-the-art skill discovery methods on both skill quality and the ability to solve downstream tasks. Videos for learned skills and code are made public on https://notmahi.github.io/disk

IROS Conference 2022 Conference Paper

Playful Interactions for Representation Learning

Sarah Young
Jyothish Pari
Pieter Abbeel
Lerrel Pinto

Ahstract- One of the key challenges in visual imitation learning is collecting large amounts of expert demonstrations for a given task. While methods for collecting human demonstrations are becoming easier with teleoperation methods and the use of low-cost assistive tools, we often still require 100–1000 demonstrations for every task to learn a visual representation and policy. To address this, we turn to an alternate form of data that does not require task-specific demonstrations - play. Playing is a fundamental method children use to learn a set of skills and behaviors and visual representations in early learning. Importantly, play data is diverse, task-agnostic, and relatively cheap to obtain. In this work, we propose to use playful interactions in a self-supervised manner to learn visual representations for downstream tasks. We collect 2 hours of playful data in 19 diverse environments and use self-predictive learning to extract visual representations. Given these representations, we train policies using imitation learning for two downstream tasks: Pushing and Stacking. We demonstrate that our visual representations generalize better than standard behavior cloning and can achieve similar performance with only half the number of required demonstrations. Our representations, which are trained from scratch, compare favorably against ImageNet pretrained representations. Finally, we provide an experimental analysis on the effects of different pretraining modes on downstream task learning.

ICLR Conference 2021 Conference Paper

Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency

Qiang Zhang
Tete Xiao
Alexei A. Efros
Lerrel Pinto
Xiaolong Wang 0004

At the heart of many robotics problems is the challenge of learning correspondences across domains. For instance, imitation learning requires obtaining correspondence between humans and robots; sim-to-real requires correspondence between physics simulators and real hardware; transfer learning requires correspondences between different robot environments. In this paper, we propose to learn correspondence across such domains emphasizing on differing modalities (vision and internal state), physics parameters (mass and friction), and morphologies (number of limbs). Importantly, correspondences are learned using unpaired and randomly collected data from the two domains. We propose dynamics cycles that align dynamic robotic behavior across two domains using a cycle consistency constraint. Once this correspondence is found, we can directly transfer the policy trained on one domain to the other, without needing any additional fine-tuning on the second domain. We perform experiments across a variety of problem domains, both in simulation and on real robots. Our framework is able to align uncalibrated monocular video of a real robot arm to dynamic state-action trajectories of a simulated arm without paired data. Video demonstrations of our results are available at: https://sites.google.com/view/cycledynamics .

NeurIPS Conference 2021 Conference Paper

RB2: Robotic Manipulation Benchmarking with a Twist

Sudeep Dasari
Jianren Wang
Joyce Hong
Shikhar Bahl
Yixin Lin
Austin Wang
Abitha Thankaraj
Karanbir Chahal

Benchmarks offer a scientific way to compare algorithms using objective performance metrics. Good benchmarks have two features: (a) they should be widely useful for many research groups; (b) and they should produce reproducible findings. In robotic manipulation research, there is a trade-off between reproducibility and broad accessibility. If the benchmark is kept restrictive (fixed hardware, objects), the numbers are reproducible but the setup becomes less general. On the other hand, a benchmark could be a loose set of protocols (e. g. object set) but the underlying variation in setups make the results non-reproducible. In this paper, we re-imagine benchmarking for robotic manipulation as state-of-the-art algorithmic implementations, alongside the usual set of tasks and experimental protocols. The added baseline implementations will provide a way to easily recreate SOTA numbers in a new local robotic setup, thus providing credible relative rankings between existing approaches and new work. However, these "local rankings" could vary between different setups. To resolve this issue, we build a mechanism for pooling experimental data between labs, and thus we establish a single global ranking for existing (and proposed) SOTA algorithms. Our benchmark, called Ranking-Based Robotics Benchmark (RB2), is evaluated on tasks that are inspired from clinically validated Southampton Hand Assessment Procedures. Our benchmark was run across two different labs and reveals several surprising findings. For example, extremely simple baselines like open-loop behavior cloning, outperform more complicated models (e. g. closed loop, RNN, Offline-RL, etc. ) that are preferred by the field. We hope our fellow researchers will use RB2 to improve their research's quality and rigor.

ICML Conference 2021 Conference Paper

Reinforcement Learning with Prototypical Representations

Denis Yarats
Rob Fergus
Alessandro Lazaric
Lerrel Pinto

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent – learning a useful representation requires diverse data, while effective exploration is only possible with coherent representations. Furthermore, we would like to learn representations that not only generalize across tasks but also accelerate downstream exploration for efficient task-specific training. To address these challenges we propose Proto-RL, a self-supervised framework that ties representation learning with exploration through prototypical representations. These prototypes simultaneously serve as a summarization of the exploratory experience of an agent as well as a basis for representing observations. We pre-train these task-agnostic representations and prototypes on environments without downstream task information. This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.

ICLR Conference 2021 Conference Paper

Self-Supervised Policy Adaptation during Deployment

Nicklas Hansen 0001
Rishabh Jangir
Yu Sun 0020
Guillem Alenyà
Pieter Abbeel
Alexei A. Efros
Lerrel Pinto
Xiaolong Wang 0004

In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new environment, we assume no prior knowledge of those changes yet still obtain significant improvements. Empirical evaluations are performed on diverse simulation environments from DeepMind Control suite and ViZDoom, as well as real robotic manipulation tasks in continuously changing environments, taking observations from an uncalibrated camera. Our method improves generalization in 31 out of 36 environments across various tasks and outperforms domain randomization on a majority of environments. Webpage and implementation: https://nicklashansen.github.io/PAD/.

IROS Conference 2021 Conference Paper

State-Only Imitation Learning for Dexterous Manipulation

Ilija Radosavovic
Xiaolong Wang 0004
Lerrel Pinto
Jitendra Malik

Modern model-free reinforcement learning methods have recently demonstrated impressive results on a number of problems. However, complex domains like dexterous manipulation remain a challenge due to the high sample complexity. To address this, current approaches employ expert demonstrations in the form of state-action pairs, which are difficult to obtain for real-world settings such as learning from videos. In this paper, we move toward a more realistic setting and explore state-only imitation learning. To tackle this setting, we train an inverse dynamics model and use it to predict actions for state-only demonstrations. The inverse dynamics model and the policy are trained jointly. Our method performs on par with state-action approaches and considerably outperforms RL alone. By not relying on expert actions, we are able to learn from demonstrations with different dynamics, morphologies, and objects. Videos available on the ${\text{project page}}$.

ICLR Conference 2021 Conference Paper

Task-Agnostic Morphology Evolution

Joey Hejna
Pieter Abbeel
Lerrel Pinto

Deep reinforcement learning primarily focuses on learning behavior, usually overlooking the fact that an agent's function is largely determined by form. So, how should one go about finding a morphology fit for solving tasks in a given environment? Current approaches that co-adapt morphology and behavior use a specific task's reward as a signal for morphology optimization. However, this often requires expensive policy optimization and results in task-dependent morphologies that are not built to generalize. In this work, we propose a new approach, Task-Agnostic Morphology Evolution (TAME), to alleviate both of these issues. Without any task or reward specification, TAME evolves morphologies by only applying randomly sampled action primitives on a population of agents. This is accomplished using an information-theoretic objective that efficiently ranks agents by their ability to reach diverse states in the environment and the causality of their actions. Finally, we empirically demonstrate that across 2D, 3D, and manipulation environments TAME can evolve morphologies that match the multi-task performance of those learned with task supervised algorithms. Our code and videos can be found at https://sites.google.com/view/task-agnostic-evolution .

NeurIPS Conference 2021 Conference Paper

URLB: Unsupervised Reinforcement Learning Benchmark

Misha Laskin
Denis Yarats
Hao Liu
Kimin Lee
Albert Zhan
Kevin Lu
Catherine Cang
Lerrel Pinto

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks. Training generalist agents that can quickly adapt to new tasks remains an outstanding challenge. Recent advances in unsupervised RL have shown that pre-training RL agents with self-supervised intrinsic rewards can result in efficient adaptation. However, these algorithms have been hard to compare and develop due to the lack of a unified benchmark. To this end, we introduce the Unsupervised Reinforcement Learning Benchmark (URLB). URLB consists of two phases: reward-free pre-training and downstream task adaptation with extrinsic rewards. Building on the DeepMind Control Suite, we provide twelve continuous control tasks from three domains for evaluation and open-source code for eight leading unsupervised RL methods. We find that the implemented baselines make progress but are not able to solve URLB and propose directions for future research.

NeurIPS Conference 2020 Conference Paper

Automatic Curriculum Learning through Value Disagreement

Yunzhi Zhang
Pieter Abbeel
Lerrel Pinto

Continually solving new, unsolved tasks is the key to learning diverse behaviors. Through reinforcement learning (RL), we have made massive strides towards solving tasks that have a single goal. However, in the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. When biological agents learn, there is often an organized and meaningful order to which learning happens. Inspired by this, we propose setting up an automatic curriculum for goals that the agent needs to solve. Our key insight is that if we can sample goals at the frontier of the set of goals that an agent is able to reach, it will provide a significantly stronger learning signal compared to randomly sampled goals. To operationalize this idea, we introduce a goal proposal module that prioritizes goals that maximize the epistemic uncertainty of the Q-function of the policy. This simple technique samples goals that are neither too hard nor too easy for the agent to solve, hence enabling continual improvement. We evaluate our method across 13 multi-goal robotic tasks and 5 navigation tasks, and demonstrate performance gains over current state-of-the-art methods.

ICLR Conference 2020 Conference Paper

Discovering Motor Programs by Recomposing Demonstrations

Tanmay Shankar
Shubham Tulsiani
Lerrel Pinto
Abhinav Gupta 0001

In this paper, we present an approach to learn recomposable motor primitives across large-scale and diverse manipulation demonstrations. Current approaches to decomposing demonstrations into primitives often assume manually defined primitives and bypass the difficulty of discovering these primitives. On the other hand, approaches in primitive discovery put restrictive assumptions on the complexity of a primitive, which limit applicability to narrow tasks. Our approach attempts to circumvent these challenges by jointly learning both the underlying motor primitives and recomposing these primitives to form the original demonstration. Through constraints on both the parsimony of primitive decomposition and the simplicity of a given primitive, we are able to learn a diverse set of motor primitives, as well as a coherent latent representation for these primitives. We demonstrate both qualitatively and quantitatively, that our learned primitives capture semantically meaningful aspects of a demonstration. This allows us to compose these primitives in a hierarchical reinforcement learning setup to efficiently solve robotic manipulation tasks like reaching and pushing. Our results may be viewed at https://sites.google.com/view/discovering-motor-programs.

NeurIPS Conference 2020 Conference Paper

Generalized Hindsight for Reinforcement Learning

Alexander Li
Lerrel Pinto
Pieter Abbeel

One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one task provides little to no signal for solving that particular task and is hence effectively wasted. However, we argue that this data, which is uninformative for one task, is likely a rich source of information for other tasks. To leverage this insight and efficiently reuse data, we present Generalized Hindsight: an approximate inverse reinforcement learning technique for relabeling behaviors with the right tasks. Intuitively, given a behavior generated under one task, Generalized Hindsight returns a different task that the behavior is better suited for. Then, the behavior is relabeled with this new task before being used by an off-policy RL optimizer. Compared to standard relabeling techniques, Generalized Hindsight provides a substantially more efficient re-use of samples, which we empirically demonstrate on a suite of multi-task navigation and manipulation tasks.

ICML Conference 2020 Conference Paper

Hierarchically Decoupled Imitation For Morphological Transfer

Joey Hejna
Lerrel Pinto
Pieter Abbeel

Learning long-range behaviors on complex high-dimensional agents is a fundamental problem in robot learning. For such tasks, we argue that transferring learned information from a morphologically simpler agent can massively improve the sample efficiency of a more complex one. To this end, we propose a hierarchical decoupling of policies into two parts: an independently learned low-level policy and a transferable high-level policy. To remedy poor transfer performance due to mismatch in morphologies, we contribute two key ideas. First, we show that incentivizing a complex agent’s low-level to imitate a simpler agent’s low-level significantly improves zero-shot high-level transfer. Second, we show that KL-regularized training of the high level stabilizes learning and prevents mode-collapse. Finally, on a suite of publicly released navigation and manipulation environments, we demonstrate the applicability of hierarchical transfer on long-range tasks across morphologies. Our code and videos can be found at https: //sites. google. com/berkeley. edu/morphology-transfer.

NeurIPS Conference 2020 Conference Paper

Reinforcement Learning with Augmented Data

Misha Laskin
Kimin Lee
Adam Stooke
Lerrel Pinto
Pieter Abbeel
Aravind Srinivas

Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are still lacking on two fronts: (a) data-efficiency of learning and (b) generalization to new environments. To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms. We perform the first extensive study of general data augmentations for RL on both pixel-based and state-based inputs, and introduce two new data augmentations - random translate and random amplitude scale. We show that augmentations such as random translate, crop, color jitter, patch cutout, random convolutions, and amplitude scale can enable simple RL algorithms to outperform complex state-of-the-art methods across common benchmarks. RAD sets a new state-of-the-art in terms of data-efficiency and final performance on the DeepMind Control Suite benchmark for pixel-based control as well as OpenAI Gym benchmark for state-based control. We further demonstrate that RAD significantly improves test-time generalization over existing methods on several OpenAI ProcGen benchmarks.

IROS Conference 2019 Conference Paper

Robot Learning via Human Adversarial Games

Jiali Duan
Qian Wang
Lerrel Pinto
C. -C. Jay Kuo
Stefanos Nikolaidis

Much work in robotics has focused on “humanin-the-loop” learning techniques that improve the efficiency of the learning process. However, these algorithms have made the strong assumption of a cooperating human supervisor that assists the robot. In reality, human observers tend to also act in an adversarial manner towards deployed robotic systems. We show that this can in fact improve the robustness of the learned models by proposing a physical framework that leverages perturbations applied by a human adversary, guiding the robot towards more robust models. In a manipulation task, we show that grasping success improves significantly when the robot trains with a human adversary as compared to training in a self-supervised manner.

ICRA Conference 2018 Conference Paper

CASSL: Curriculum Accelerated Self-Supervised Learning

Adithyavairavan Murali
Lerrel Pinto
Dhiraj Gandhi
Abhinav Gupta 0001

Recent self-supervised learning approaches focus on using a few thousand data points to learn policies for high-level, low-dimensional action spaces. However, scaling this framework for higher-dimensional control requires either scaling up the data collection efforts or using a clever sampling strategy for training. We present a novel approach - Curriculum Accelerated Self-Supervised Learning (CASSL) - to train policies that map visual information to high-level, higher-dimensional action spaces. CASSL orders the sampling of training data based on control dimensions: the learning and sampling are focused on few control parameters before other parameters. The right curriculum for learning is suggested by variance-based global sensitivity analysis of the control space. We apply our CASSL framework to learning how to grasp using an adaptive, underactuated multi-fingered gripper, a challenging system to control. Our experimental results indicate that CASSL provides significant improvement and generalization compared to baseline methods such as staged curriculum learning (8% increase) and complete end-to-end learning with random exploration (14% improvement) tested on a set of novel objects.

NeurIPS Conference 2018 Conference Paper

Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias

Abhinav Gupta
Adithyavairavan Murali
Dhiraj Prakashchand Gandhi
Lerrel Pinto

Data-driven approaches to solving robotic tasks have gained a lot of traction in recent years. However, most existing policies are trained on large-scale datasets collected in curated lab settings. If we aim to deploy these models in unstructured visual environments like people's homes, they will be unable to cope with the mismatch in data distribution. In such light, we present the first systematic effort in collecting a large dataset for robotic grasping in homes. First, to scale and parallelize data collection, we built a low cost mobile manipulator assembled for under 3K USD. Second, data collected using low cost robots suffer from noisy labels due to imperfect execution and calibration errors. To handle this, we develop a framework which factors out the noise as a latent variable. Our model is trained on 28K grasps collected in several houses under an array of different environmental conditions. We evaluate our models by physically executing grasps on a collection of novel objects in multiple unseen homes. The models trained with our home dataset showed a marked improvement of 43. 7% over a baseline model trained with data collected in lab. Our architecture which explicitly models the latent noise in the dataset also performed 10% better than one that did not factor out the noise. We hope this effort inspires the robotics community to look outside the lab and embrace learning based approaches to handle inaccurate cheap robots.

IROS Conference 2017 Conference Paper

Learning to fly by crashing

Dhiraj Gandhi
Lerrel Pinto
Abhinav Gupta 0001

How do you learn to navigate an Unmanned Aerial Vehicle (UAV) and avoid obstacles? One approach is to use a small dataset collected by human experts: however, high capacity learning algorithms tend to overfit when trained with little data. An alternative is to use simulation. But the gap between simulation and real world remains large especially for perception problems. The reason most research avoids using large-scale real data is the fear of crashes! In this paper, we propose to bite the bullet and collect a dataset of crashes itself! We build a drone whose sole purpose is to crash into objects: it samples naive trajectories and crashes into random objects. We crash our drone 11, 500 times to create one of the biggest UAV crash dataset. This dataset captures the different ways in which a UAV can crash. We use all this negative flying data in conjunction with positive data sampled from the same trajectories to learn a simple yet powerful policy for UAV navigation. We show that this simple self-supervised model is quite effective in navigating the UAV even in extremely cluttered environments with dynamic obstacles including humans. For supplementary video see: .

ICRA Conference 2017 Conference Paper

Learning to push by grasping: Using multiple tasks for effective learning

Lerrel Pinto
Abhinav Gupta 0001

Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due to their huge data requirements for learning a task. The argument of the difficulty in scalability to multiple tasks is well founded, since training these tasks often require hundreds or thousands of examples. But do end-to-end approaches need to learn a unique model for every task? Intuitively, it seems that sharing across tasks should help since all tasks require some common understanding of the environment. In this paper, we attempt to take the next step in data-driven end-to-end learning frameworks: move from the realm of task-specific models to joint learning of multiple robot tasks. In an astonishing result we show that models with multi-task learning tend to perform better than task-specific models trained with same amounts of data. For example, a deep-network learned with 2. 5K grasp and 2. 5K push examples performs better on grasping than a network trained on 5K grasp examples.

NeurIPS Conference 2017 Conference Paper

Predictive-State Decoders: Encoding the Future into Recurrent Networks

Arun Venkatraman
Nicholas Rhinehart
Wen Sun
Lerrel Pinto
Martial Hebert
Byron Boots
Kris Kitani
J. Bagnell

Recurrent neural networks (RNNs) are a vital modeling technique that rely on internal states learned indirectly by optimization of a supervised, unsupervised, or reinforcement training loss. RNNs are used to model dynamic processes that are characterized by underlying latent states whose form is often unknown, precluding its analytic representation inside an RNN. In the Predictive-State Representation (PSR) literature, latent state processes are modeled by an internal state representation that directly models the distribution of future observations, and most recent work in this area has relied on explicitly representing and targeting sufficient statistics of this probability distribution. We seek to combine the advantages of RNNs and PSRs by augmenting existing state-of-the-art recurrent neural networks with Predictive-State Decoders (PSDs), which add supervision to the network's internal state representation to target predicting future observations. PSDs are simple to implement and easily incorporated into existing training pipelines via additional loss regularization. We demonstrate the effectiveness of PSDs with experimental results in three different domains: probabilistic filtering, Imitation Learning, and Reinforcement Learning. In each, our method improves statistical performance of state-of-the-art recurrent baselines and does so with fewer iterations and less data.

ICML Conference 2017 Conference Paper

Robust Adversarial Reinforcement Learning

Lerrel Pinto
James Davidson
Rahul Sukthankar
Abhinav Gupta 0001

Deep neural networks coupled with fast simulation and improved computational speeds have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based approaches fail to generalize since: (a) the gap between simulation and real world is so large that policy-learning approaches fail to transfer; (b) even if policy learning is done in real world, the data scarcity leads to failed generalization from training to test scenarios (e. g. , due to different friction or object masses). Inspired from H-infinity control methods, we note that both modeling errors and differences in training and test scenarios can just be viewed as extra forces/disturbances in the system. This paper proposes the idea of robust adversarial reinforcement learning (RARL), where we train an agent to operate in the presence of a destabilizing adversary that applies disturbance forces to the system. The jointly trained adversary is reinforced – that is, it learns an optimal destabilization policy. We formulate the policy learning as a zero-sum, minimax objective function. Extensive experiments in multiple environments (InvertedPendulum, HalfCheetah, Swimmer, Hopper, Walker2d and Ant) conclusively demonstrate that our method (a) improves training stability; (b) is robust to differences in training/test conditions; and c) outperform the baseline even in the absence of the adversary.

ICRA Conference 2017 Conference Paper

Supervision via competition: Robot adversaries for learning tasks

Lerrel Pinto
James Davidson
Abhinav Gupta 0001

There has been a recent paradigm shift in robotics to data-driven learning for planning and control. Due to large number of experiences required for training, most of these approaches use a self-supervised paradigm: using sensors to measure success/failure. However, in most cases, these sensors provide weak supervision at best. In this work, we propose an adversarial learning framework that pits an adversary against the robot learning the task. In an effort to defeat the adversary, the original robot learns to perform the task with more robustness leading to overall improved performance. We show that this adversarial framework forces the robot to learn a better grasping model in order to overcome the adversary. By grasping 82% of presented novel objects compared to 68% without an adversary, we demonstrate the utility of creating adversaries. We also demonstrate via experiments that having robots in adversarial setting might be a better learning strategy as compared to having collaborative multiple robots. For supplementary video see: youtu.be/QfK3Bqhc6Sk

ICRA Conference 2016 Conference Paper

Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours

Lerrel Pinto
Abhinav Gupta 0001

Current model free learning-based robot grasping approaches exploit human-labeled datasets for training the models. However, there are two problems with such a methodology: (a) since each object can be grasped in multiple ways, manually labeling grasp locations is not a trivial task; (b) human labeling is biased by semantics. While there have been attempts to train robots using trial-and-error experiments, the amount of data used in such experiments remains substantially low and hence makes the learner prone to over-fitting. In this paper, we take the leap of increasing the available training data to 40 times more than prior work, leading to a dataset size of 50K data points collected over 700 hours of robot grasping attempts. This allows us to train a Convolutional Neural Network (CNN) for the task of predicting grasp locations without severe overfitting. In our formulation, we recast the regression problem to an 18-way binary classification over image patches. We also present a multi-stage learning approach where a CNN trained in one stage is used to collect hard negatives in subsequent stages. Our experiments clearly show the benefit of using large-scale datasets (and multi-stage training) for the task of grasping. We also compare to several baselines and show state-of-the-art performance on generalization to unseen objects for grasping.