Search Results for author:
Found 1 papers, 0 papers with code
An Elementary Proof that Q-learning Converges Almost Surely
Watkins' and Dayan's Q-learning is a model-free reinforcement learning algorithm that iteratively refines an estimate for the optimal action-value function of an MDP by stochastically "visiting" many state-ation pairs [Watkins and Dayan, 1992].
Cannot find the paper you are looking for? You can
Submit a new open access paper.
