Factored Reinforcement Learning (frl) is a new technique to solve Factored Markov Decision Problems (fmdps) when the structure of the problem is not known in advance. Like Anticipa...
Olivier Sigaud, Martin V. Butz, Olga Kozlova, Chri...
Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning ...
Temporal difference (TD) learning has been used to learn strong evaluation functions in a variety of two-player games. TD-gammon illustrated how the combination of game tree search...
We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-b...
TD-FALCON is a self-organizing neural network that incorporates Temporal Difference (TD) methods for reinforcement learning. Despite the advantages of fast and stable learning, TD...