Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration
This work addresses variance reduction for policy gradients in robot control and similar domains, presenting an incremental improvement over existing methods.
The paper tackles the challenge of reducing variance in policy gradient estimates for reinforcement learning in continuous action spaces, combining parameter-based exploration, importance sampling, and an optimal baseline to achieve efficient sample reuse and reliable policy updates, with experimental validation showing effectiveness.
The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy gradient estimates for reliable policy updates. In this paper, we combine the following three ideas and give a highly effective policy gradient method: (a) the policy gradients with parameter based exploration, which is a recently proposed policy search method with low variance of gradient estimates, (b) an importance sampling technique, which allows us to reuse previously gathered data in a consistent way, and (c) an optimal baseline, which minimizes the variance of gradient estimates with their unbiasedness being maintained. For the proposed method, we give theoretical analysis of the variance of gradient estimates and show its usefulness through extensive experiments.