Benchmarking Potential Based Rewards for Learning Humanoid Locomotion
Name
2307.10142.pdf
Size
2.5 MB
Format
Adobe PDF
Checksum (MD5)
159faefb361b8a66a55da53f902210c1
Author(s)
Jeon, Se Hwan
Heim, Steve
Khazoom, Charles
Kim, Sangbae
Date Issued
May 29, 2023
Journal
2023 IEEE International Conference on Robotics and Automation (ICRA)
Publisher
IEEE
Citation
Jeon, Se Hwan, Heim, Steve, Khazoom, Charles and Kim, Sangbae. 2023. "Benchmarking Potential Based Rewards for Learning Humanoid Locomotion." 2023 IEEE International Conference on Robotics and Automation (ICRA).
Version
Author's final manuscript
Abstract
The main challenge in developing effective reinforcement learning (RL) pipelines is often the design and tuning the reward functions. Well-designed shaping reward can lead to significantly faster learning. Naively formulated rewards, however, can conflict with the desired behavior and result in overfitting or even erratic performance if not properly tuned. In theory, the broad class of potential based reward shaping (PBRS) can help guide the learning process without affecting the optimal policy. Although several studies have explored the use of potential based reward shaping to accelerate learning convergence, most have been limited to grid-worlds and low-dimensional systems, and RL in robotics has predominantly relied on standard forms of reward shaping. In this paper, we benchmark standard forms of shaping with PBRS for a humanoid robot. We find that in this high-dimensional system, PBRS has only marginal benefits in convergence speed. However, the PBRS reward terms are significantly more robust to scaling than typical reward shaping approaches, and thus easier to tune.
Description
2023 IEEE International Conference on Robotics and Automation (ICRA 2023) May 29 - June 2, 2023. London, UK
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/icra48891.2023.10160885
