Separated Trust Regions Policy Optimization Method
published: March 2, 2020, recorded: August 2019, views: 4
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
In this work, we propose a moderate policy update method for reinforcement learning, which encourages the agent to explore more boldly in early episodes but updates the policy more cautious. Based on the maximum entropy framework, we propose a softer objective with more conservative constraints and build the separated trust regions for optimization. To reduce the variance of expected entropy return, a calculated state policy entropy of Gaussian distribution is preferred instead of collecting log probability by sampling. This new method, which we call separated trust region for policy mean and variance (STRMV), can be view as an extension to proximal policy optimization (PPO) but it is gentler for policy update and more lively for exploration. We test our approach on a wide variety of continuous control benchmark tasks in the MuJoCo environment. The experiments demonstrate that STRMV outperforms the previous state of art on-policy methods, not only achieving higher rewards but also improving the sample efficiency.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !