方策勾配法における誘導探索のための最適制御ベースのベースライン
Optimal Control-Based Baseline for Guided Exploration in Policy Gradient Methods
強化学習の方策勾配法において、最適制御問題の価値関数をベースラインとして用いることで、分散低減だけでなく誘導的な探索を実現し、疎な報酬環境でのロボット学習で有効性を示した論文。
著者: Xubo Lyu, Site Li, Seth Siriya, Ye Pu, Mo Chen
分類: cs.LG, cs.AI, cs.RO, cs.SY, eess.SY
原文アブストラクト
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.
