不変方策最適化:強化学習におけるより強い汎化に向けて
Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning
訓練環境間で共通に最適となる不変表現を学習するIPOを提案し、未知環境への汎化性能を向上させた。
著者: Anoopkumar Sonar, Vincent Pacelli, Anirudha Majumdar
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training. In this paper, we approach this challenge through the following invariance principle: an agent must find a representation such that there exists an action-predictor built on top of this representation that is simultaneously optimal across all training domains. Intuitively, the resulting invariant policy enhances generalization by finding causes of successful actions. We propose a novel learning algorithm, Invariant Policy Optimization (IPO), that implements this principle and learns an invariant policy during training. We compare our approach with standard policy gradient methods and demonstrate significant improvements in generalization performance on unseen domains for linear quadratic regulator and grid-world problems, and an example where a robot must learn to open doors with varying physical properties.
