ダイナミクス差異を補正する強化学習：ドメイン分類器による転移学習
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
ソースとターゲットの遷移を識別する補助分類器を学習し、その出力で報酬を修正することで、明示的なダイナミクスモデルなしにドメイン適応を実現する手法を提案した論文。
著者: Benjamin Eysenbach, Swapnil Asawa, Shreyas Chaudhari, Sergey Levine, Ruslan Salakhutdinov
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target domain. Building off of a probabilistic view of RL, we formally show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function. This modified reward function is simple to estimate by learning auxiliary classifiers that distinguish source-domain transitions from target-domain transitions. Intuitively, the modified reward function penalizes the agent for visiting states and taking actions in the source domain which are not possible in the target domain. Said another way, the agent is penalized for transitions that would indicate that the agent is interacting with the source domain, rather than the target domain. Our approach is applicable to domains with continuous states and actions and does not require learning an explicit model of the dynamics. On discrete and continuous control tasks, we illustrate the mechanics of our approach and demonstrate its scalability to high-dimensional tasks.
