Fast deep reinforcement learning using online adjustments from the past
Steven Hansen, Alexander Pritzel, Pablo Sprechmann, Andre Barreto, Charles Blundell
–Neural Information Processing Systems
We propose Ephemeral V alue Adjusments (EV A): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer.
Neural Information Processing Systems
Nov-20-2025, 21:21:33 GMT
- Country:
- North America > Canada > Quebec > Montreal (0.04)
- Industry:
- Health & Medicine (0.47)
- Leisure & Entertainment > Games
- Computer Games (0.47)
- Technology: