ICML
2005
IEEE
15 years 10 days ago
2005
IEEE
Several algorithms for learning near-optimal policies in Markov Decision Processes have been analyzed and proven efficient. Empirical results have suggested that Model-based Inter...
ICML
2005
IEEE
15 years 10 days ago
2005
IEEE
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...