Timezone: »

Offline Reinforcement Learning on Real Robot with Realistic Data Sources
Gaoyue Zhou · Liyiming Ke · Siddhartha Srinivasa · Abhinav Gupta · Aravind Rajeswaran · Vikash Kumar
Event URL: https://openreview.net/forum?id=Lf4m-z6i8m »

Offline Reinforcement Learning (ORL) provides a framework to train control policies from fixed sub-optimal datasets, making it suitable for safety-critical applications like robotics. Despite significant algorithmic advances and benchmarking in simulation, the evaluation of ORL algorithms on real-world robot learning tasks has been limited. Since real robots are sensitive to details like sensor noises, reset conditions, demonstration sources, and test time distribution, it remains a question whether ORL is a competitive solution to real robotic challenges and what would characterize such tasks. We aim to address this deficiency through an empirical study of representative ORL algorithms on four table-top manipulation tasks using a Franka-Panda robot arm. Our evaluation finds that for scenarios with sufficient in-domain data of high quality, specialized ORL algorithms can be competitive with the behavior cloning approach. However, for scenarios that require out-of-distribution generalization or task transfer, ORL algorithms can learn and generalize from offline heterogeneous datasets and outperform behavior cloning. Project URL: https://sites.google.com/view/real-orl-anon

Author Information

Gaoyue Zhou (Carnegie Mellon University)
Liyiming Ke (Paul G Allen School of Computer Science & Engineering, University of Washington)
Siddhartha Srinivasa (Carnegie Mellon University)
Abhinav Gupta (Facebook AI Research/CMU)
Aravind Rajeswaran (FAIR)
Vikash Kumar (FAIR, Meta-AI)
Vikash Kumar

I am currently a research scientist at Facebook AI Research (FAIR). I have also spent some time at Google-Brain, OpenAI and Berkeley Artificial Intelligence Research (BAIR) Lab. I did my PhD at CSE, University of Washington's Movement Control Lab, under the supervision of Prof. Emanuel Todorov and Prof. Sergey Levine. I am interested in the areas of Robotics, and Embodied Artificial Intelligence. My general interest lies in developing artificial agents that are cheap, portable and exhibit complex behaviors.

More from the Same Authors