Explaining RL Decisions With Trajectories

Abstract

Explanation is a key component for the adoption of reinforcement learning (RL) in many real-world decision-making problems. In the literature, the explanation is often provided by saliency attribution to the features of the RL agent's state. In this work, we propose a complementary approach to these explanations, particularly for offline RL, where we attribute the policy decisions of a trained RL agent to the trajectories encountered by it during training. To do so, we encode trajectories in offline training data individually as well as collectively (encoding a set of trajectories). We then attribute policy decisions to a set of trajectories in this encoded space by estimating the sensitivity of the decision with respect to that set. Further, we demonstrate the effectiveness of the proposed approach in terms of quality of attributions as well as practical scalability in diverse environments that involve both discrete and continuous state and action spaces such as grid-worlds, video gam

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydeshmukh2023explaining

Related papers

• Explaining Reinforcement Learning Policies Through Counterfactual Trajectories (2022)0.00
• Experiential Explanations For Reinforcement Learning (2022)2.26
• Abstracted Trajectory Visualization For Explainability In Reinforcement Learning (2024)2.26
• Explaining Conditions For Reinforcement Learning Behaviors From Real And Imagined Data (2020)0.00
• Offline Safe Reinforcement Learning Using Trajectory Classification (2024)0.00
• Contrastive Explanations For Reinforcement Learning In Terms Of Expected Consequences (2018)0.00
• Local And Global Explanations Of Agent Behavior: Integrating Strategy Summaries With Saliency Maps (2020)11.85
• Explainable Reinforcement Learning Via Temporal Policy Decomposition (2025)0.00