Optimal Control-Based Baseline for Guided Exploration in Policy Gradient Methods

Abstract

In this paper, a novel optimal control-based baseline function is presented for the policy gradient method in deep reinforcement learning (RL). The baseline is obtained by computing the value function of an optimal control problem, which is formed to be closely associated with the RL task. In contrast to the traditional baseline aimed at variance reduction of policy gradient estimates, our work utilizes the optimal control value function to introduce a novel aspect to the role of baseline -- providing guided exploration during policy learning. This aspect is less discussed in prior works. We validate our baseline on robot learning tasks, showing its effectiveness in guided exploration, particularly in sparse reward environments.

References in corpus (7)

• Continuous control with deep reinforcement learning
• Playing Atari with Deep Reinforcement Learning
• Trust Region Policy Optimization
• Addressing Function Approximation Error in Actor-Critic Methods
• Model-Ensemble Trust-Region Policy Optimization
• Benchmarking Model-Based Reinforcement Learning
• FaSTrack: a Modular Framework for Real-Time Motion Planning and Guaranteed Safe Tracking