2 search results - page 1 / 1 » Provably Near-Optimal Sampling-Based Policies for Stochastic... |
MOR
2007
15 years 2 months ago
2007
143
click to vote
IJCAI
2001
15 years 4 months ago
2001
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...