Off-Policy Temporal-Difference Learning with Function Approximation

We 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? - Indico
Meyn. Control Techniques for Complex Networks. Cambridge University Press, 2007. See last chapter on simulation and average-cost TD learning.
1 Temporal Difference and Q-Learning
Q-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 ...
Reinforcement Learning
Temporal Difference (TD) methods are a class of model-free reinforcement learning algorithms. TD methods combine ideas from Monte Carlo methods and Dynamic.



Autres Cours:

MDP and RL: Q-learning, stochastic approximation