Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations

By Connor Mattson, Anurag Sidharth Aribandi, and Daniel S. Brown

Reinforcement Learning Journal, vol. 4, 2024, pp. 1822–1840.

Presented at the Reinforcement Learning Conference (RLC), Amherst Massachusetts, August 9–12, 2024.


Download:

Abstract:

We study the problem of cross-embodiment inverse reinforcement learning, where we wish to learn a reward function from video demonstrations in one or more embodiments and then transfer the learned reward to a different embodiment (e.g., different action space, dynamics, size, shape, etc.). Learning reward functions that transfer across embodiments is important in settings such as teaching a robot a policy via human video demonstrations or teaching a robot to imitate a policy from another robot with a different embodiment. However, prior work has only focused on cases where near-optimal demonstrations are available, which is often difficult to ensure. By contrast, we study the setting of cross-embodiment reward learning from mixed-quality demonstrations. We demonstrate that prior work struggles to learn generalizable reward representations when learning from mixed-quality data. We then analyze several techniques that leverage human feedback for representation learning and alignment to enable effective cross-embodiment learning. Our results give insight into how different representation learning techniques lead to qualitatively different reward shaping behaviors and the importance of human feedback when learning from mixed-quality, mixed-embodiment data.


Citation Information:

Connor Mattson, Anurag Sidharth Aribandi, and Daniel S Brown. "Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations." Reinforcement Learning Journal, vol. 4, 2024, pp. 1822–1840.

BibTeX:

@article{mattson2024representation,
    title={Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations},
    author={Mattson, Connor and Aribandi, Anurag Sidharth and Brown, Daniel S.},
    journal={Reinforcement Learning Journal},
    volume={4},
    pages={1822--1840},
    year={2024}
}