Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning

TL;DR

This paper applies inverse reinforcement learning to enable bipedal robots to learn adaptable locomotion strategies from demonstrations, improving performance over complex terrains.

Contribution

It introduces IRL algorithms for learning reward functions in bipedal locomotion, providing insights into expert strategies and enhancing policy adaptability.

Findings

Learned reward functions reveal meaningful locomotion strategies.

Training with inferred rewards improves performance on unseen terrains.

IRL enhances adaptability of bipedal walking policies.

Abstract

Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments. Recent advancements in learning from demonstrations have shown promising results for robot learning in complex environments. While imitation learning of expert policies has been well-explored, the study of learning expert reward functions is largely under-explored in legged locomotion. This paper brings state-of-the-art Inverse Reinforcement Learning (IRL) techniques to solving bipedal locomotion problems over complex terrains. We propose algorithms for learning expert reward functions, and we subsequently analyze the learned functions. Through nonlinear function approximation, we uncover meaningful insights into the expert's locomotion strategies. Furthermore, we empirically demonstrate that training a bipedal locomotion policy with the inferred reward functions enhances its walking performance on unseen terrains, highlighting the adaptability offered by reward learning.