Parameter Critic: a Model Free Variance Reduction Method Through Imperishable Samples

Abstract

We consider the problem of finding a policy that maximizes an expected reward throughout the trajectory of an agent that interacts with an unknown environment. Frequently denoted Reinforcement Learning, this framework suffers from the need of large amount of samples in each step of the learning process. To this end, we introduce parameter critic, a formulation that allows samples to keep their validity even when the parameters of the policy change. In particular, we propose the use of a function approximator to directly learn the relationship between the parameters and the expected cumulative reward. Through convergence analysis, we demonstrate the parameter critic outperforms gradient-free parameter space exploration techniques as it is robust to noise. Empirically, we show that our method solves the cartpole problem which corroborates our claim as the agent can successfully learn an optimal policy while learning the relationship between the parameters and the cumulative reward.