Title | ||
---|---|---|
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models. |
Abstract | ||
---|---|---|
Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric function approximators, such as deep networks. In this paper, we study how to bridge this gap, by employing uncertainty-aware dynamics models. We propose a new algorithm called probabilistic ensembles with trajectory sampling (PETS) that combines uncertainty-aware deep network dynamics models with sampling-based uncertainty propagation. Our comparison to state-of-the-art model-based and model-free deep RL algorithms shows that our approach matches the asymptotic performance of model-free algorithms on several challenging benchmark tasks, while requiring significantly fewer samples (e.g., 8 and 125 times fewer samples than Soft Actor Critic and Proximal Policy Optimization respectively on the half-cheetah task). |
Year | Venue | Keywords |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | network dynamics,deep reinforcement learning,actor critic |
DocType | Volume | ISSN |
Conference | 31 | 1049-5258 |
Citations | PageRank | References |
21 | 0.62 | 22 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chua, Kurtland | 1 | 21 | 0.62 |
Roberto Calandra | 2 | 105 | 13.42 |
Rowan McAllister | 3 | 44 | 5.18 |
Sergey Levine | 4 | 3377 | 182.21 |