Auto-Encoding Adversarial Imitation Learning

Kaifeng Zhang, Rui Zhao, Ziming Zhang, Yang Gao

Keywords: imitation learning, reinforcement learning, auto-encoders

TL;DR: this paper presents a new adversarial imitation learning method based on auto-encoding

Abstract: Reinforcement learning (RL) provides a powerful framework for decision-making, but its application in practice often requires a carefully designed reward function. Adversarial Imitation Learning (AIL) sheds light on automatic policy acquisition without access to the reward signal from the environment. In this work, we propose Auto-Encoding Adversarial Imitation Learning (AEAIL), a robust and scalable AIL framework. To induce expert policies from demonstrations, AEAIL utilizes the reconstruction error of an auto-encoder as a reward signal, which provides more information for optimizing policies than the prior discriminator-based ones. Subsequently, we use the derived objective functions to train the auto-encoder and the agent policy. Experiments show that our AEAIL performs superior compared to state-of-the-art methods in the MuJoCo environments. More importantly, AEAIL shows much better robustness when the expert demonstrations are noisy. Specifically, our method achieves $11\%$ and $50.7\%$ relative improvement overall compared to the best baseline GAIL and PWIL on clean and noisy expert data, respectively. Video results, open-source code and dataset are available in supplementary materials.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)