MDP and RL: Q-learning, stochastic approximation
TD samples one-step and uses a previous estimation of V . ? DP needs all possible values of V (s?). MC: One full trajectory for update TD: ...
Off-Policy Temporal-Difference Learning with Function ApproximationWe introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off- policy learning is of ... Why Does Q-learning Work? - IndicoMeyn. Control Techniques for Complex Networks. Cambridge University Press, 2007. See last chapter on simulation and average-cost TD learning. 1 Temporal Difference and Q-LearningQ-learning is an off-policy learning algorithm. An on-policy learning algorithm learns the value of the policy being carried out by the agent. (ii) Model-based ...
Autres Cours:
