Explainable Reinforcement Learning Via Temporal Policy Decomposition

Abstract

We investigate the explainability of Reinforcement Learning (RL) policies from a temporal perspective, focusing on the sequence of future outcomes associated with individual actions. In RL, value functions compress information about rewards collected across multiple trajectories and over an infinite horizon, allowing a compact form of knowledge representation. However, this compression obscures the temporal details inherent in sequential decision-making, presenting a key challenge for interpretability. We present Temporal Policy Decomposition (TPD), a novel explainability approach that explains individual RL actions in terms of their Expected Future Outcome (EFO). These explanations decompose generalized value functions into a sequence of EFOs, one for each time step up to a prediction horizon of interest, revealing insights into when specific outcomes are expected to occur. We leverage fixed-horizon temporal difference learning to devise an off-policy method for learning EFOs for both

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyruggeri2025explainable

Related papers

• From Explainability To Interpretability: Interpretable Policies In Reinforcement Learning Via Model Explanation (2025)0.00
• Disentangling Dynamics And Returns: Value Function Decomposition With Future Prediction (2019)0.00
• Experiential Explanations For Reinforcement Learning (2022)2.26
• Open The Black Box: Step-based Policy Updates For Temporally-correlated Episodic Reinforcement Learning (2024)0.00
• Foresee Then Evaluate: Decomposing Value Estimation With Latent Future Prediction (2021)3.58
• Generation Of Policy-level Explanations For Reinforcement Learning (2019)11.39
• Explaining RL Decisions With Trajectories (2023)0.00
• Explaining An Agent's Future Beliefs Through Temporally Decomposing Future Reward Estimators (2024)0.00