Reinforcement Learning › Methods ›

Value Iteration

79 directly classified papers

Papers per year

Papers

Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs NIPS 2007

Theoretical Analysis of Heuristic Search Methods for Online POMDPs NIPS 2007

Stable Dual Dynamic Programming NIPS 2007

Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning NIPS 2006