Abstract | ||
---|---|---|
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by planning over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning. We show that EVA is performant on a demonstration task and Atari games. |
Year | Venue | Keywords |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | deep reinforcement learning,neural network,atari games |
DocType | Volume | ISSN |
Conference | 31 | 1049-5258 |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Steven Stenberg Hansen | 1 | 19 | 5.33 |
Pablo Sprechmann | 2 | 625 | 24.21 |
Alexander Pritzel | 3 | 1 | 0.35 |
André Barreto | 4 | 12 | 5.65 |
Charles Blundell | 5 | 822 | 41.64 |