Convergence of the Q-ae Learning on Deterministic MDPs and Its Efficiency on the Stochastic Environment Gang ZHAOShoji TATSUMIRuoying SUN
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 2000/09/25 Vol. E83-ANo. 9pp. 1786-1795 Type of Manuscript: PAPER Category: Algorithms and Data Structures Keyword: Q-learning, Q-ae learning, exploration, dynamic programming, planning,
RTP-Q: A Reinforcement Learning System with Time Constraints Exploration Planning for Accelerating the Learning Rate Gang ZHAOShoji TATSUMIRuoying SUN
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 1999/10/25 Vol. E82-ANo. 10pp. 2266-2273 Type of Manuscript: PAPER Category: Artificial Intelligence and Knowledge Keyword: reinforcement learning, planning, reacting, exploration, exploitation,