Deep residual reinforcement learning
<p>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...
Main Authors: | Zhang, S, Boehmer, W, Whiteson, S |
---|---|
Format: | Conference item |
Language: | English |
Published: |
International Foundation for Autonomous Agents and Multiagent Systems
2020
|
Similar Items
-
Transient non−stationarity and generalisation in deep reinforcement learning
by: Igl, M, et al.
Published: (2021) -
Deep coordination graphs
by: Boehmer, W, et al.
Published: (2020) -
Bayesian action decoder for deep multi-agent reinforcement learning
by: Whiteson, S
Published: (2019) -
UneVEn: Universal value exploration for multi-agent reinforcement learning
by: Gupta, T, et al.
Published: (2021) -
Deep variational reinforcement learning for POMDPs
by: Igl, M, et al.
Published: (2018)