@inproceedings{11e1296f889149809dd79dcf3ecbbc51,
title = "BAIL: Best-Action Imitation Learning for batch deep reinforcement learning",
abstract = "There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment. We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for both simplicity and performance. BAIL learns a V function, uses the V function to select actions it believes to be high-performing, and then uses those actions to train a policy network using imitation learning. For the MuJoCo benchmark, we provide a comprehensive experimental study of BAIL, comparing its performance to four other batch Q-learning and imitation-learning schemes for a large variety of batch datasets. Our experiments show that BAIL{\textquoteright}s performance is much higher than the other schemes, and is also computationally much faster than the batch Q-learning schemes.",
author = "Xinyue Chen and Zijian Zhou and Zheng Wang and Che Wang and Yanqiu Wu and Keith Ross",
year = "2020",
language = "English",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural Information Processing Systems (NIPS) Foundation",
editor = "H. Larochelle and M. Ranzato and R. Hadsell and Balcan, \{M. F.\} and H. Lin",
booktitle = "34th Conference on Neural Information Processing Systems (NeurIPS 2020)",
note = "34th Conference on Neural Information Processing Systems, NeurIPS 2020 ; Conference date: 06-12-2020 Through 12-12-2020",
}