Model-based reinforcement learning
Chelsea Finn
Coauthor of SimPLe, which uses a learned video model for Atari reinforcement learning.
- Tracked papers
- 1
- Past year
- 0
- Editor picks
- 0
Model-Based Reinforcement Learning for Atari
SimPLe (Simulated Policy Learning) trains a video prediction model of an Atari game and learns a policy inside it, using only 100k environment interactions, about two hours of real-time play.