论文标题
从真实和想象的数据中解释加强学习行为的条件
Explaining Conditions for Reinforcement Learning Behaviors from Real and Imagined Data
论文作者
论文摘要
在现实世界中，强化学习（RL）的部署在校准用户信任和期望方面面临挑战。作为开发能够传达其能力的RL系统的一步，我们提出了一种生成人解剖的抽象行为模型的方法，该模型可以识别经验性条件，从而导致不同的任务执行策略和结果。我们的方法包括从状态表示形式中提取体验特征，从轨迹中抽象策略描述以及训练可解释的决策树，该决策树可以确定最可预测不同RL行为的条件。我们演示了我们的方法，该方法是从与环境的相互作用以及来自训练有素的概率世界模型中的轨迹数据产生的轨迹数据。
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.
