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...
| Autors principals: | , , |
|---|---|
| Format: | Conference item |
| Idioma: | English |
| Publicat: |
International Foundation for Autonomous Agents and Multiagent Systems
2020
|