We prove the convergence of an actor/critic algorithm that is equivalent to Q-learning by construction. Its equivalence is achieved by encoding Q-values within the policy and value function of the actor and critic. The resultant actor/critic algorithm is novel in two ways: it updates the critic only when the most probable action is executed from any given state, and it rewards the actor using c...

We establish the coefficient necessary and sufficient conditions for existence of solutions weakly nonlinear boundary-value problems systems ordinary differential equations with pulsed action at fixed times propose an iterative algorithm construction these solutions.

In reinforcement learning, an agent collects information interacting with an environment and uses it to derive a behavior. This paper focuses on efficient sampling; that is, the problem of choosing the interaction samples so that the corresponding behavior tends quickly to the optimal behavior. Our main result is a sensitivity analysis relating the choice of sampling any stateaction pair to the...