Abstract | ||
---|---|---|
We interpret meta-reinforcement learning as the problem of learning how to quickly find a good sampling distribution in a new environment. This interpretation leads to the development of two new meta-reinforcement learning algorithms: E-MAML and E-RL2. Results are presented on a new environment we call 'Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning. Further results are presented on a set of maze environments. We show E-MAML and E-RL2 deliver better performance than baseline algorithms on both tasks. |
Year | Venue | Field |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | Computer science,Artificial intelligence,Machine learning,Reinforcement learning |
DocType | Volume | ISSN |
Journal | 31 | 1049-5258 |
Citations | PageRank | References |
6 | 0.44 | 9 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
bradly c stadie | 1 | 82 | 6.02 |
Ge Yang | 2 | 12 | 1.57 |
Rein Houthooft | 3 | 600 | 21.07 |
Xi Chen | 4 | 399 | 31.78 |
Yan Duan | 5 | 775 | 27.97 |
Yuhuai Wu | 6 | 6 | 0.44 |
Pieter Abbeel | 7 | 6363 | 376.48 |
Ilya Sutskever | 8 | 25814 | 1120.24 |