XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques
Not on the map. Why?
Abstract (arXiv)
Reinforcement Learning (RL) has demonstrated substantial potential across diverse fields, yet understanding its decision-making process, especially in real-world scenarios where rationality and safety are paramount, is an ongoing challenge. This paper delves in to Explainable RL (XRL), a subfield of Explainable AI (XAI) aimed at unravelling the complexities of RL models. Our focus rests on state-explaining techniques, a crucial subset within XRL methods, as they reveal the underlying factors influencing an agent's actions at any given time. Despite their significant role, the lack of a unified evaluation framework hinders assessment of their accuracy and effectiveness. To address this, we introduce XRL-Bench, a unified standardized benchmark tailored for the evaluation and comparison of XRL methods, encompassing three main modules: standard RL environments, explainers based on state importance, and standard evaluators. XRL-Bench supports both tabular and image data for state explanation. We also propose TabularSHAP, an innovative and competitive XRL method. We demonstrate the practical utility of TabularSHAP in real-world online gaming services and offer an open-source benchmark platform for the straightforward implementation and evaluation of XRL methods. Our contributions facilitate the continued progression of XRL technology.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 65 references that are in the map. First posted on arXiv 20 Feb 2024.
Builds on
43 of 65 references.
References · 43
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017Counterfactual Multi-Agent Policy Gradientscited by 733
- 2017Interpretation of Neural Networks is Fragilecited by 443
- 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
- 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 279
- 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
31 more
- 2018Techniques for Interpretable Machine Learningcited by 237
- 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
- 2018Verifiable Reinforcement Learning via Policy Extractioncited by 176
- 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
- 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 150
- 2017Visualizing and Understanding Atari Agentscited by 141
- 2020Explainable Reinforcement Learning: A Surveycited by 139
- 2019Language as an Abstraction for Hierarchical Deep Reinforcement Learningcited by 138
- 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
- 2018Model Agnostic Supervised Local Explanationscited by 83
- 2019Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptionscited by 81
- 2020Explainable Artificial Intelligence: a Systematic Reviewcited by 79
- 2017Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learningcited by 77
- 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
- 2019Shapley Q-value: A Local Reward Approach to Solve Global Reward Gamescited by 71
- 2019Neural Logic Reinforcement Learningcited by 53
- 2017The Promise and Peril of Human Evaluation for Model Interpretabilitycited by 52
- 2019Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attributioncited by 50
- 2021The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learningcited by 50
- 2017Interpretable Policies for Reinforcement Learning by Genetic Programmingcited by 47
- 2020A Boolean Task Algebra for Reinforcement Learningcited by 46
- 2021ELLA: Exploration through Learned Language Abstractioncited by 42
- 2018Transparency and Explanation in Deep Reinforcement Learning Neural Networkscited by 40
- 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
- 2019Social Attention for Autonomous Decision-Making in Dense Trafficcited by 39
- 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 38
- 2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
- 2019Improving performance of deep learning models with axiomatic attribution priors and expected gradientscited by 32
- 2022A Survey of Explainable Reinforcement Learningcited by 31
- 2020Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programmingcited by 12
- 2018Autonomous Self-Explanation of Behavior for Interactive Reinforcement Learning Agentscited by 10
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.