Author name cluster

Philemon Brakel

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.

5 papers

2 author rows

IROS Conference 2025 Conference Paper

Exploiting Policy Idling for Dexterous Manipulation

Annie S. Chen
Philemon Brakel
Antonia Bronars
Annie Xie
Sandy Han Huang
Oliver Groth
Maria Bauzá 0001
Markus Wulfmeier

Learning based methods for dexterous manipulation have made notable progress in recent years, and they can now produce solutions to complex tasks. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that can be observed across many settings is that policies idle, i. e. they cease to move beyond a small region of states, often indefinitely, when they reach certain states. This policy idling is often a reflection of the training data. For instance, it can occur when the data contains small actions in areas where the robot needs to perform high-precision motions, e. g. , when preparing to grasp an object or object insertion. Prior works have tried to mitigate this phenomenon e. g. by filtering the training data or modifying the control frequency. However, these approaches can negatively impact policy performance in other ways. As an alternative, we investigate how to leverage the detectability of idling behavior to inform exploration and policy improvement. Our approach, Pause-Induced Perturbations (PIP), applies perturbations at detected idling states, thus helping it to escape problematic basins of attraction. On a range of challenging simulated dual-arm tasks, we find that this simple approach can already noticeably improve test-time performance, with no additional supervision or training. Furthermore, since the robot tends to idle at critical points in a movement, we also find that learning from the resulting episodes leads to better iterative policy improvement compared to prior approaches. Our perturbation strategy also leads to a 15-35% improvement in absolute success rate on a real-world insertion task that requires complex multi-finger manipulation.

Details

ICML Conference 2024 Conference Paper

Offline Actor-Critic Reinforcement Learning Scales to Large Models

Jost Tobias Springenberg
Abbas Abdolmaleki
Jingwei Zhang 0001
Oliver Groth
Michael Bloesch
Thomas Lampe
Philemon Brakel
Sarah Bechtle

We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outperform strong, supervised, behavioral cloning baselines for multi-task training on a large dataset; containing both sub-optimal and expert behavior on 132 continuous control tasks. We introduce a Perceiver-based actor-critic model and elucidate the key features needed to make offline RL work with self- and cross-attention modules. Overall, we find that: i) simple offline actor critic algorithms are a natural choice for gradually moving away from the currently predominant paradigm of behavioral cloning, and ii) via offline RL it is possible to learn multi-task policies that master many domains simultaneously, including real robotics tasks, from sub-optimal demonstrations or self-generated data.

Details

IROS Conference 2022 Conference Paper

Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner

Philemon Brakel
Steven Bohez
Leonard Hasenclever
Nicolas Heess
Konstantinos Bousmalis

We propose a simple imitation learning procedure for learning locomotion controllers that can walk over very challenging terrains. We use trajectory optimization (TO) to produce a large dataset of trajectories over procedurally generated terrains and use Reinforcement Learning (RL) to imitate these trajectories. We demonstrate with a realistic model of the ANYmal robot that the learned controllers transfer to unseen terrains and provide an effective initialization for fine-tuning on challenging terrains that require exteroception and precise foot placements. Our setup combines TO and RL in a simple fashion that overcomes the computational limitations and need for a robust tracking controller of the former and the exploration and reward-tuning difficulties of the latter.

Details

ICML Conference 2016 Conference Paper

Deconstructing the Ladder Network Architecture

Mohammad Pezeshki
Linxi Fan
Philemon Brakel
Aaron C. Courville
Yoshua Bengio

The Ladder Network is a recent new approach to semi-supervised learning that turned out to be very successful. While showing impressive performance, the Ladder Network has many components intertwined, whose contributions are not obvious in such a complex architecture. This paper presents an extensive experimental investigation of variants of the Ladder Network in which we replaced or removed individual components to learn about their relative importance. For semi-supervised tasks, we conclude that the most important contribution is made by the lateral connections, followed by the application of noise, and the choice of what we refer to as the ‘combinator function’. As the number of labeled training examples increases, the lateral connections and the reconstruction criterion become less important, with most of the generalization improvement coming from the injection of noise in each layer. Finally, we introduce a combinator function that reduces test error rates on Permutation-Invariant MNIST to 0. 57% for the supervised setting, and to 0. 97% and 1. 0% for semi-supervised settings with 1000 and 100 labeled examples, respectively.

Details

JMLR Journal 2012 Journal Article

Oger: Modular Learning Architectures For Large-Scale Sequential Processing

David Verstraeten
Benjamin Schrauwen
Sander Dieleman
Philemon Brakel
Pieter Buteneers
Dejan Pecevski

Oger (OrGanic Environment for Reservoir computing) is a Python toolbox for building, training and evaluating modular learning architectures on large data sets. It builds on MDP for its modularity, and adds processing of sequential data sets, gradient descent training, several cross-validation schemes and parallel parameter optimization methods. Additionally, several learning algorithms are implemented, such as different reservoir implementations (both sigmoid and spiking), ridge regression, conditional restricted Boltzmann machine (CRBM) and others, including GPU accelerated versions. Oger is released under the GNU LGPL, and is available from http://organic.elis.ugent.be/oger. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2012. ( edit, beta )

PDF Details