Author name cluster

Sherry Yang 0001

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.

16 papers

1 author row

ICLR Conference 2025 Conference Paper

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

Shicong Cen
Jincheng Mei
Katayoon Goshvadi
Hanjun Dai
Tong Yang 0007
Sherry Yang 0001
Dale Schuurmans
Yuejie Chi

Reinforcement learning from human feedback (RLHF) has demonstrated great promise in aligning large language models (LLMs) with human preference. Depending on the availability of preference data, both online and offline RLHF are active areas of investigation. A key bottleneck is understanding how to incorporate uncertainty estimation in the reward function learned from the preference data for RLHF, regardless of how the preference data is collected. While the principles of optimism or pessimism under uncertainty are well-established in standard reinforcement learning (RL), a practically-implementable and theoretically-grounded form amenable to large language models is not yet available, as standard techniques for constructing confidence intervals become intractable under arbitrary policy parameterizations. In this paper, we introduce a unified approach to online and offline RLHF --- value-incentivized preference optimization (VPO) --- which regularizes the maximum-likelihood estimate of the reward function with the corresponding value function, modulated by a sign to indicate whether the optimism or pessimism is chosen. VPO also directly optimizes the policy with implicit reward modeling, and therefore shares a simpler RLHF pipeline similar to direct preference optimization. Theoretical guarantees of VPO are provided for both online and offline settings, matching the rates of their standard RL counterparts. Moreover, experiments on text summarization, dialogue, and standard benchmarks verify the practicality and effectiveness of VPO.

ICML Conference 2024 Conference Paper

Code as Reward: Empowering Reinforcement Learning with VLMs

David Venuto
Mohammad Sami Nur Islam
Martin Klissarov
Doina Precup
Sherry Yang 0001
Ankit Anand

Pre-trained Vision-Language Models (VLMs) are able to understand visual concepts, describe and decompose complex tasks into sub-tasks, and provide feedback on task completion. In this paper, we aim to leverage these capabilities to support the training of reinforcement learning (RL) agents. In principle, VLMs are well suited for this purpose, as they can naturally analyze image-based observations and provide feedback (reward) on learning progress. However, inference in VLMs is computationally expensive, so querying them frequently to compute rewards would significantly slowdown the training of an RL agent. To address this challenge, we propose a framework named Code as Reward (VLM-CaR). VLM-CaR produces dense reward functions from VLMs through code generation, thereby significantly reducing the computational burden of querying the VLM directly. We show that the dense rewards generated through our approach are very accurate across a diverse set of discrete and continuous environments, and can be more effective in training RL policies than the original sparse environment rewards.

ICLR Conference 2024 Conference Paper

Learning Interactive Real-World Simulators

Sherry Yang 0001
Yilun Du
Seyed Kamyar Seyed Ghasemipour
Jonathan Tompson
Leslie Pack Kaelbling
Dale Schuurmans
Pieter Abbeel

Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by humans, robots, and other interactive agents. Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world. We explore the possibility of learning a universal simulator (UniSim) of real-world interaction through generative modeling. We first make the important observation that natural datasets available for learning a real-world simulator are often rich along different axes (e.g., abundant objects in image data, densely sampled actions in robotics data, and diverse movements in navigation data). With careful orchestration of diverse datasets, each providing a different aspect of the overall experience, UniSim can emulate how humans and agents interact with the world by simulating the visual outcome of both high-level instructions such as “open the drawer” and low-level controls such as “move by x,y” from otherwise static scenes and objects. There are numerous use cases for such a real-world simulator. As an example, we use UniSim to train both high-level vision-language planners and low-level reinforcement learning policies, each of which exhibit zero-shot real-world transfer after training purely in a learned real-world simulator. We also show that other types of intelligence such as video captioning models can benefit from training with simulated experience in UniSim, opening up even wider applications.

ICML Conference 2024 Conference Paper

Position: Video as the New Language for Real-World Decision Making

Sherry Yang 0001
Jacob C. Walker
Jack Parker-Holder
Yilun Du
Jake Bruce
André Barreto 0001
Pieter Abbeel
Dale Schuurmans

Both text and video data are abundant on the internet and support large-scale self-supervised learning through next token or frame prediction. However, they have not been equally leveraged: language models have had significant real-world impact, whereas video generation has remained largely limited to media entertainment. Yet video data captures important information about the physical world that is difficult to express in language. To address this gap, we discuss an under-appreciated opportunity to extend video generation to solve tasks in the real world. We observe how, akin to language, video can serve as a unified interface that can absorb internet knowledge and represent diverse tasks. Moreover, we demonstrate how, like language models, video generation can serve as planners, agents, compute engines, and environment simulators through techniques such as in-context learning, planning and reinforcement learning. We identify major impact opportunities in domains such as robotics, self-driving, and science, supported by recent work that demonstrates how such advanced capabilities in video generation are plausibly within reach. Lastly, we identify key challenges in video generation that mitigate progress. Addressing these challenges will enable video generation models to demonstrate unique value alongside language models in a wider array of AI applications.

ICLR Conference 2024 Conference Paper

Probabilistic Adaptation of Black-Box Text-to-Video Models

Sherry Yang 0001
Yilun Du
Bo Dai 0001
Dale Schuurmans
Joshua B. Tenenbaum
Pieter Abbeel

Large text-to-video models trained on internet-scale data have demonstrated exceptional capabilities in generating high-fidelity videos from arbitrary textual descriptions. However, similar to proprietary language models, large text-to-video models are often black boxes whose weight parameters are not publicly available, posing a significant challenge to adapting these models to specific domains such as robotics, animation, and personalized stylization. Inspired by how a large language model can be prompted to perform new tasks without access to the model weights, we investigate how to adapt a black-box pretrained text-to-video model to a variety of downstream domains without weight access to the pretrained model. In answering this question, we propose \emph{\methodname}, which leverages the score function of a large pretrained video diffusion model as a probabilistic prior to guide the generation of a task-specific small video model. Our experiments show that, by incorporating broad knowledge and fidelity of the pretrained model probabilistically, a small model with as few as 1.25% parameters of the pretrained model can generate high-quality yet domain-specific videos for a variety of downstream domains such as animation, egocentric modeling, and modeling of simulated and real-world robotics data. As large text-to-video models starting to become available as a service similar to large language models, we advocate for private institutions to expose scores of video diffusion models as outputs in addition to generated videos to allow flexible adaptation of large pretrained text-to-video models by the general public.

ICLR Conference 2024 Conference Paper

Scalable Diffusion for Materials Generation

Sherry Yang 0001
KwangHwan Cho
Amil Merchant
Pieter Abbeel
Dale Schuurmans
Igor Mordatch
Ekin Dogus Cubuk

Generative models trained on internet-scale data are capable of generating novel and realistic texts, images, and videos. A natural next question is whether these models can advance science, for example by generating novel stable materials. Traditionally, models with explicit structures (e.g., graphs) have been used in modeling structural relationships in scientific data (e.g., atoms and bonds in crystals), but generating structures can be difficult to scale to large and complex systems. Another challenge in generating materials is the mismatch between standard generative modeling metrics and downstream applications. For instance, common metrics such as the reconstruction error do not correlate well with the downstream goal of discovering novel stable materials. In this work, we tackle the scalability challenge by developing a unified crystal representation that can represent any crystal structure (UniMat), followed by training a diffusion probabilistic model on these UniMat representations. Our empirical results suggest that despite the lack of explicit structure modeling, UniMat can generate high fidelity crystal structures from larger and more complex chemical systems, outperforming previous graph-based approaches under various generative modeling metrics. To better connect the generation quality of materials to downstream applications, such as discovering novel stable materials, we propose additional metrics for evaluating generative models of materials, including per-composition formation energy and stability with respect to convex hulls through decomposition energy from Density Function Theory (DFT). Lastly, we show that conditional generation with UniMat can scale to previously established crystal datasets with up to millions of crystals structures, outperforming random structure search (the current leading method for structure discovery) in discovering new stable materials.

ICLR Conference 2024 Conference Paper

Video Language Planning

Yilun Du
Sherry Yang 0001
Pete Florence
Fei Xia 0002
Ayzaan Wahid
Brian Ichter
Pierre Sermanet
Tianhe Yu

We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data. To this end, we present video language planning (VLP), an algorithm that consists of a tree search procedure, where we train (i) vision-language models to serve as both policies and value functions, and (ii) text-to-video models as dynamics models. VLP takes as input a long-horizon task instruction and current image observation, and outputs a long video plan that provides detailed multimodal (video and language) specifications that describe how to complete the final task. VLP scales with increasing computation budget where more computation time results in improved video plans, and is able to synthesize long-horizon video plans across different robotics domains -- from multi-object rearrangement, to multi-camera bi-arm dexterous manipulation. Generated video plans can be translated into real robot actions via goal-conditioned policies, conditioned on each intermediate frame of the generated video. Experiments show that VLP substantially improves long-horizon task success rates compared to prior methods on both simulated and real robots (across 3 hardware platforms).

ICLR Conference 2023 Conference Paper

Dichotomy of Control: Separating What You Can Control from What You Cannot

Sherry Yang 0001
Dale Schuurmans
Pieter Abbeel
Ofir Nachum

Future- or return-conditioned supervised learning is an emerging paradigm for offline reinforcement learning (RL), in which the future outcome (i.e., return) associated with a sequence of actions in an offline dataset is used as input to a policy trained to imitate those same actions. While return-conditioning is at the heart of popular algorithms such as decision transformer (DT), these methods tend to perform poorly in highly stochastic environments, where an occasional high return associated with a sequence of actions may be due more to the randomness of the environment than to the actions themselves. Such situations can lead to a learned policy that is inconsistent with its conditioning inputs; i.e., using the policy – while conditioned on a specific desired return – to act in the environment can lead to a distribution of real returns that is wildly different than desired. In this work, we propose the dichotomy of control (DoC), a future-conditioned supervised learning framework that separates mechanisms within a policy’s control (actions) from those outside of a policy’s control (environment stochasticity). We achieve this by conditioning the policy on a latent variable representation of the future and designing a mutual information constraint that removes any future information from the latent variable that is only due to randomness of the environment. Theoretically, we show that DoC yields policies that are consistent with their conditioning inputs, ensuring that conditioning a learned policy on a desired high-return future outcome will correctly induce high-return behavior. Empirically, we show that DoC is able to achieve significantly better performance than DT on environments with highly stochastic rewards (e.g., Bandit) and transitions (e.g., FrozenLake).

ICML Conference 2023 Conference Paper

Multi-Environment Pretraining Enables Transfer to Action Limited Datasets

David Venuto
Sherry Yang 0001
Pieter Abbeel
Doina Precup
Igor Mordatch
Ofir Nachum

Using massive datasets to train large-scale models has emerged as a dominant approach for broad generalization in natural language and vision applications. In reinforcement learning, however, a key challenge is that available data of sequential decision making is often not annotated with actions - for example, videos of game-play are much more available than sequences of frames paired with their logged game controls. We propose to circumvent this challenge by combining large but sparsely-annotated datasets from a target environment of interest with fully-annotated datasets from various other source environments. Our method, Action Limited PreTraining (ALPT), leverages the generalization capabilities of inverse dynamics modelling (IDM) to label missing action data in the target environment. We show that utilizing even one additional environment dataset of labelled data during IDM pretraining gives rise to substantial improvements in generating action labels for unannotated sequences. We evaluate our method on benchmark game-playing environments and show that we can significantly improve game performance and generalization capability compared to other approaches, using annotated datasets equivalent to only $12$ minutes of gameplay. Highlighting the power of IDM, we show that these benefits remain even when target and source environments share no common actions.

ICLR Conference 2023 Conference Paper

Offline RL for Natural Language Generation with Implicit Language Q Learning

Charlie Victor Snell
Ilya Kostrikov
Yi Su
Sherry Yang 0001
Sergey Levine

Large language models distill broad knowledge from text corpora. However, they can be inconsistent when it comes to completing user specified tasks. This issue can be addressed by finetuning such models via supervised learning on curated datasets, or via reinforcement learning. In this work, we propose a novel offline RL method, implicit language Q-learning (ILQL), designed for use on language models, that combines both the flexible utility maximization framework of RL algorithms with the ability of supervised learning to leverage previously collected data, as well as its simplicity and stability. Our method employs a combination of value conservatism alongside an implicit dataset support constraint in learning value functions, which are then used to guide language model generations towards maximizing user-specified utility functions. In addition to empirically validating ILQL, we present a detailed empirical analysis of situations where offline RL can be useful in natural language generation settings, demonstrating how it can be a more effective utility optimizer than prior approaches for end-to-end dialogue, and how it can effectively optimize high variance reward functions based on subjective judgement, such as whether to label a comment as toxic or not.

ICML Conference 2022 Conference Paper

Making Linear MDPs Practical via Contrastive Representation Learning

Tianjun Zhang
Tongzheng Ren
Sherry Yang 0001
Joseph E. Gonzalez
Dale Schuurmans
Bo Dai 0001

It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations. This motivates much of the recent theoretical study on linear MDPs. However, most approaches require a given representation under unrealistic assumptions about the normalization of the decomposition or introduce unresolved computational challenges in practice. Instead, we consider an alternative definition of linear MDPs that automatically ensures normalization while allowing efficient representation learning via contrastive estimation. The framework also admits confidence-adjusted index algorithms, enabling an efficient and principled approach to incorporating optimism or pessimism in the face of uncertainty. To the best of our knowledge, this provides the first practical representation learning method for linear MDPs that achieves both strong theoretical guarantees and empirical performance. Theoretically, we prove that the proposed algorithm is sample efficient in both the online and offline settings. Empirically, we demonstrate superior performance over existing state-of-the-art model-based and model-free algorithms on several benchmarks.

ICML Conference 2022 Conference Paper

Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization

Hanjun Dai
Sherry Yang 0001
Yuan Xue 0001
Dale Schuurmans
Bo Dai 0001

Distributions over discrete sets capture the essential statistics including the high-order correlation among elements. Such information provides powerful insight for decision making across various application domains, e. g. , product assortment based on product distribution in shopping carts. While deep generative models trained on pre-collected data can capture existing distributions, such pre-trained models are usually not capable of aligning with a target domain in the presence of distribution shift due to reasons such as temporal shift or the change in the population mix. We develop a general framework to adapt a generative model subject to a (possibly counterfactual) target data distribution with both sampling and computation efficiency. Concretely, instead of re-training a full model from scratch, we reuse the learned modules to preserve the correlations between set elements, while only adjusting corresponding components to align with target marginal constraints. We instantiate the approach for three commonly used forms of discrete set distribution—latent variable, autoregressive, and energy based models—and provide efficient solutions for marginal-constrained optimization in either primal or dual forms. Experiments on both synthetic and real-world e-commerce and EHR datasets show that the proposed framework is able to practically align a generative model to match marginal constraints under distribution shift.

ICLR Conference 2022 Conference Paper

TRAIL: Near-Optimal Imitation Learning with Suboptimal Data

Sherry Yang 0001
Sergey Levine
Ofir Nachum

In imitation learning, one aims to learn task-solving policies using access to near-optimal expert trajectories collected from the task environment. However, high-quality trajectories -- e.g., from human experts -- can be expensive to obtain in practical settings. On the contrary, it is often much easier to obtain large amounts of suboptimal trajectories which can nevertheless provide insight into the structure of the environment, showing what \emph{could} be done in the environment even if not what \emph{should} be done. Is it possible to formalize these conceptual benefits and devise algorithms to use offline datasets to yield \emph{provable} improvements to the sample-efficiency of imitation learning? In this work, we answer this question affirmatively and present training objectives which use an offline dataset to learn an approximate \emph{factored} dynamics model whose structure enables the extraction of a \emph{latent action space}. Our theoretical analysis shows that the learned latent action space can boost the sample-efficiency of downstream imitation learning, effectively reducing the need for large near-optimal expert datasets through the use of auxiliary non-expert data. We evaluate the practicality of our objective through experiments on a set of navigation and locomotion tasks. Our results verify the benefits suggested by our theory and show that our algorithms is able to recover near-optimal policies with fewer expert trajectories.

ICLR Conference 2021 Conference Paper

Benchmarks for Deep Off-Policy Evaluation

Justin Fu
Mohammad Norouzi 0002
Ofir Nachum
George Tucker
Ziyu Wang 0001
Alexander Novikov 0001
Sherry Yang 0001
Michael R. Zhang

Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making. The ability to learn offline is particularly important in many real-world domains, such as in healthcare, recommender systems, or robotics, where online data collection is an expensive and potentially dangerous process. Being able to accurately evaluate and select high-performing policies without requiring online interaction could yield significant benefits in safety, time, and cost for these applications. While many OPE methods have been proposed in recent years, comparing results between papers is difficult because currently there is a lack of a comprehensive and unified benchmark, and measuring algorithmic progress has been challenging due to the lack of difficult evaluation tasks. In order to address this gap, we present a collection of policies that in conjunction with existing offline datasets can be used for benchmarking off-policy evaluation. Our tasks include a range of challenging high-dimensional continuous control problems, with wide selections of datasets and policies for performing policy selection. The goal of our benchmark is to provide a standardized measure of progress that is motivated from a set of principles designed to challenge and test the limits of existing OPE methods. We perform an evaluation of state-of-the-art algorithms and provide open-source access to our data and code to foster future research in this area.

ICML Conference 2021 Conference Paper

Representation Matters: Offline Pretraining for Sequential Decision Making

Sherry Yang 0001
Ofir Nachum

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research area, known as offline RL, has largely focused on offline policy optimization, aiming to find a return-maximizing policy exclusively from offline data. In this paper, we consider a slightly different approach to incorporating offline data into sequential decision-making. We aim to answer the question, what unsupervised objectives applied to offline datasets are able to learn state representations which elevate performance on downstream tasks, whether those downstream tasks be online RL, imitation learning from expert demonstrations, or even offline policy optimization based on the same offline dataset? Through a variety of experiments utilizing standard offline RL datasets, we find that the use of pretraining with unsupervised learning objectives can dramatically improve the performance of policy learning algorithms that otherwise yield mediocre performance on their own. Extensive ablations further provide insights into what components of these unsupervised objectives {–} e. g. , reward prediction, continuous or discrete representations, pretraining or finetuning {–} are most important and in which settings.

ICML Conference 2020 Conference Paper

Energy-Based Processes for Exchangeable Data

Sherry Yang 0001
Bo Dai 0001
Hanjun Dai
Dale Schuurmans

Recently there has been growing interest in modeling sets with exchangeability such as point clouds. A shortcoming of current approaches is that they restrict the cardinality of the sets considered or can only express limited forms of distribution over unobserved data. To overcome these limitations, we introduce Energy-Based Processes (EBPs), which extend energy based models to exchangeable data while allowing neural network parameterizations of the energy function. A key advantage of these models is the ability to express more flexible distributions over sets without restricting their cardinality. We develop an efficient training procedure for EBPs that demonstrates state-of-the-art performance on a variety of tasks such as point cloud generation, classification, denoising, and image completion