5k citations · 11k across the 51 of their papers we have counts for
53 papers
Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning
Cristina Pinneri, Sarah Bechtle, Markus Wulfmeier +4
We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional in…
Policy composition in reinforcement learning via multi-objective policy optimization
Shruti Mishra, Ankit Anand, Jordan Hoffmann +4
We enable reinforcement learning agents to learn successful behavior policies by utilizing relevant pre-existing teacher policies. The teacher policies are introduced as objectives…
Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World
Nico Gürtler, Felix Widmaier, Cansu Sancaktar +21
Experimentation on real robots is demanding in terms of time and costs. For this reason, a large part of the reinforcement learning (RL) community uses simulators to develop and be…
Towards A Unified Agent with Foundation Models
Norman Di Palo, Arunkumar Byravan, Leonard Hasenclever +3
Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and pla…
Towards practical reinforcement learning for tokamak magnetic control
Brendan D. Tracey, Andrea Michi, Yuri Chervonyi +15
Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbac…
RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
Konstantinos Bousmalis, Giulia Vezzani, Dushyant Rao +36
The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learnin…
A Generalist Dynamics Model for Control
Ingmar Schubert, Jingwei Zhang, Jake Bruce +7
We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen environments, bo…
Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains
Jingwei Zhang, Jost Tobias Springenberg, Arunkumar Byravan +5
In this paper we study the problem of learning multi-step dynamics prediction models (jumpy models) from unlabeled experience and their utility for fast inference of (high-level) p…
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration
Giulia Vezzani, Dhruva Tirumala, Markus Wulfmeier +13
The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common a…
Solving Continuous Control via Q-learning
Tim Seyde, Peter Werner, Wilko Schwarting +4
While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the as…
MO2: Model-Based Offline Options
Sasha Salter, Markus Wulfmeier, Dhruva Tirumala +4
The ability to discover useful behaviours from past experience and transfer them to new tasks is considered a core component of natural embodied intelligence. Inspired by neuroscie…
Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach
Bobak Shahriari, Abbas Abdolmaleki, Arunkumar Byravan +6
Actor-critic algorithms that make use of distributional policy evaluation have frequently been shown to outperform their non-distributional counterparts on many challenging control…
The Challenges of Exploration for Offline Reinforcement Learning
Nathan Lambert, Markus Wulfmeier, William Whitney +5
Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal…
Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies
Tim Seyde, Igor Gilitschenski, Wilko Schwarting +4
Reinforcement learning (RL) for continuous control typically employs distributions whose support covers the entire action space. In this work, we investigate the colloquially known…
Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes
Alex X. Lee, Coline Devin, Yuxiang Zhou +18
We study the problem of robotic stacking with objects of complex geometry. We propose a challenging and diverse set of such objects that was carefully designed to require strategie…
Evaluating model-based planning and planner amortization for continuous control
Arunkumar Byravan, Leonard Hasenclever, Piotr Trochim +8
There is a widespread intuition that model-based control methods should be able to surpass the data efficiency of model-free approaches. In this paper we attempt to evaluate this i…
Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
Oliver Groth, Markus Wulfmeier, Giulia Vezzani +5
Curiosity-based reward schemes can present powerful exploration mechanisms which facilitate the discovery of solutions for complex, sparse or long-horizon tasks. However, as the ag…
Collect & Infer -- a fresh look at data-efficient Reinforcement Learning
Martin Riedmiller, Jost Tobias Springenberg, Roland Hafner +1
This position paper proposes a fresh look at Reinforcement Learning (RL) from the perspective of data-efficiency. Data-efficient RL has gone through three major stages: pure on-lin…
On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning
Abbas Abdolmaleki, Sandy H. Huang, Giulia Vezzani +11
Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional ob…
Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning
William F. Whitney, Michael Bloesch, Jost Tobias Springenberg +3
Despite the close connection between exploration and sample efficiency, most state of the art reinforcement learning algorithms include no considerations for exploration beyond max…
Representation Matters: Improving Perception and Exploration for Robotics
Markus Wulfmeier, Arunkumar Byravan, Tim Hertweck +8
Projecting high-dimensional environment observations into lower-dimensional structured representations can considerably improve data-efficiency for reinforcement learning in domain…
"What, not how": Solving an under-actuated insertion task from scratch
Giulia Vezzani, Michael Neunert, Markus Wulfmeier +7
Robot manipulation requires a complex set of skills that need to be carefully combined and coordinated to solve a task. Yet, most ReinforcementLearning (RL) approaches in robotics…
Local Search for Policy Iteration in Continuous Control
Jost Tobias Springenberg, Nicolas Heess, Daniel Mankowitz +10
We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framew…
Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification
Daniel J. Mankowitz, Dan A. Calian, Rae Jeong +5
Many real-world physical control systems are required to satisfy constraints upon deployment. Furthermore, real-world systems are often subject to effects such as non-stationarity,…