Abstract
We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we introduce the concept of an alpha-policy that stands as a locally superior policy. By adaptively modifying the value, we can effectively manage the influence of analytical policy gradients during learning. To this end, we suggest metrics for assessing the variance and bias of analytical gradients, reducing dependence on these gradients when high variance or bias is detected. Our proposed approach outperforms baseline algorithms in various scenarios, such as function optimization, physics simulations, and traffic control environments.
Ryan Sullivan
Computer Science PhD Student
rsulli@umd.edu
My research interests include reinforcement learning, curriculum learning, and training agents in multi-agent or open-ended environments.