A Model-Based Actor-Critic Algorithm in Continuous Time and Space
Résumé
This paper presents a model-based actor-critic algorithm in continuous time and space. Two function approximators are used: one learns the policy (the actor) and the other learns the state-value function (the critic). The critic learns with the TD(lambda) algorithm and the actor by gradient ascent on the Hamiltonian. A similar algorithm had been proposed by Doya, but this one is more general. This algorithm was applied successfully to teach simulated articulated robots to swim.
Loading...