@inproceedings{282fcc3e86ef4ed5a4bf361a3363a0c9,
title = "Deep residual reinforcement learning",
abstract = "We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we find the residual algorithm an effective approach to the distribution mismatch problem in model-based planning. Compared with the existing TD(k) method, our residual-based method makes weaker assumptions about the model and yields a greater performance boost.",
keywords = "Reinforcement learning, Residual algorithms",
author = "Shangtong Zhang and Wendelin Boehmer and Shimon Whiteson",
year = "2020",
language = "English",
series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",
pages = "1611--1619",
editor = "Bo An and {El Fallah Seghrouchni}, Amal and Gita Sukthankar",
booktitle = "Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020",
note = "19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 ; Conference date: 19-05-2020",
}