11 papers
Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics
Leonard Hinckeldey, Elliot Fosong, Rimvydas Rubavicius +6
As embodied autonomous systems capable of assisting humans in daily activities remain a major goal for robotics, efficient and appropriate reinforcement learning (RL) simulation te…
roto 2.0: The Robot Tactile Olympiad
Elle Miller, Jayaram Reddy, Ayush Deshmukh +4
Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympia…
CODA: Coordination via On-Policy Diffusion for Multi-Agent Offline Reinforcement Learning
Marcel Hedman, Kale-ab Abebe Tessera, Juan Claude Formanek +5
Offline multi-agent reinforcement learning (MARL) enables policy learning from fixed datasets, but is prone to coordination failure: agents trained on static, off-policy data conve…
Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning
Weipu Zhang, Adam Jelley, Trevor McInroe +2
While deep reinforcement learning (RL) from pixels has achieved remarkable success, its sample inefficiency remains a critical limitation for real-world applications. Model-based R…
Forgetting is Everywhere
Ben Sanati, Thomas L. Lee, Trevor McInroe +5
A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data. Addressing this problem requires a principle…
Efficient Offline Reinforcement Learning: First Imitate, then Improve
Adam Jelley, Trevor McInroe, Sam Devlin +1
Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization ob…