REACT: Revealing Evolutionary Action Consequence Trajectories For Interpretable Reinforcement Learning

Abstract

To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during training, we posit that considering a range of edge-case trajectories provides a more comprehensive understanding of their inherent behavior. To induce such scenarios, we introduce a disturbance to the initial state, optimizing it through an evolutionary algorithm to generate a diverse population of demonstrations. To evaluate the fitness of trajectories, REACT incorporates a joint fitness function that encourages both local and global diversity in the encountered states and chosen actions. Through assessments with policies trained for varying durations in discrete and continuous environments, we demonstrate the descriptive power of REACT. Our results highlight its effectiveness in revealing nuanced aspects of RL models' behavior beyond optim

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyaltmann2024react

Related papers

• Explaining Reinforcement Learning Policies Through Counterfactual Trajectories (2022)0.00
• ACTER: Diverse And Actionable Counterfactual Sequences For Explaining And Diagnosing RL Policies (2024)0.00
• REVEAL-IT: Reinforcement Learning With Visibility Of Evolving Agent Policy For Interpretability (2024)0.00
• Explaining Conditions For Reinforcement Learning Behaviors From Real And Imagined Data (2020)0.00
• Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes (2023)5.84
• Contrastive Explanations For Reinforcement Learning In Terms Of Expected Consequences (2018)0.00
• Experiential Explanations For Reinforcement Learning (2022)2.26
• Continuous Action Reinforcement Learning From A Mixture Of Interpretable Experts (2020)0.00