Explaining Conditions For Reinforcement Learning Behaviors From Real And Imagined Data

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyacharya2020explaining

Related papers

• Experiential Explanations For Reinforcement Learning (2022)2.26
• Explaining Reinforcement Learning Policies Through Counterfactual Trajectories (2022)0.00
• Contrastive Explanations For Reinforcement Learning In Terms Of Expected Consequences (2018)0.00
• Explaining RL Decisions With Trajectories (2023)0.00
• Abstracted Trajectory Visualization For Explainability In Reinforcement Learning (2024)2.26
• Explainable Reinforcement Learning Via Model Transforms (2022)0.00
• Acting Upon Imagination: When To Trust Imagined Trajectories In Model Based Reinforcement Learning (2021)0.00
• An Empirical Investigation Of The Challenges Of Real-world Reinforcement Learning (2020)0.00