Offline Reinforcement Learning Workshop
Neural Information Processing Systems (NeurIPS)
December 12, 2020
@OfflineRL ยท #OFFLINERL2020
Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
- Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo, Ofir Nachum, Shixiang Gu