実データと想像データから強化学習の行動条件を説明する
Explaining Conditions for Reinforcement Learning Behaviors from Real and Imagined Data
強化学習エージェントの行動戦略や結果を予測する条件を、実環境と学習済み世界モデルが生成した想像軌道の両方から解釈可能な決定木で抽出する手法を提案した論文。
著者: Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
分類: cs.LG, cs.AI, cs.HC, cs.NE, cs.RO
原文アブストラクト
The deployment of reinforcement learning (RL) in the real world comes with challenges in calibrating user trust and expectations. As a step toward developing RL systems that are able to communicate their competencies, we present a method of generating human-interpretable abstract behavior models that identify the experiential conditions leading to different task execution strategies and outcomes. Our approach consists of extracting experiential features from state representations, abstracting strategy descriptors from trajectories, and training an interpretable decision tree that identifies the conditions most predictive of different RL behaviors. We demonstrate our method on trajectory data generated from interactions with the environment and on imagined trajectory data that comes from a trained probabilistic world model in a model-based RL setting.
