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 and relative improvement overall compared to the best baseline FAIRL and PWIL on clean and noisy expert data, respectively. Video results, open-source code and dataset are available in https://sites.google.com/view/auto-encoding-imitation.
View on arXiv