{"total":177,"rows":[{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59,"area":null},{"id":"2104.04413","title":"Provable Repair of Deep Neural Networks","created":"2021-04-09","cited_by_count":42,"area":null},{"id":"2303.03226","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","created":"2023-03-06","cited_by_count":42,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2405.15383","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","created":"2024-05-24","cited_by_count":40,"area":"wm"},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2104.02466","title":"A Review of Formal Methods applied to Machine Learning","created":"2021-04-06","cited_by_count":33,"area":null},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32,"area":null},{"id":"2102.13045","title":"Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods","created":"2021-02-25","cited_by_count":31,"area":null},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31,"area":null},{"id":"2410.10807","title":"HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees","created":"2024-10-14","cited_by_count":31,"area":null},{"id":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"area":null},{"id":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2405.14956","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","created":"2024-05-23","cited_by_count":18,"area":"deeprl"},{"id":"2205.13728","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","created":"2022-05-27","cited_by_count":16,"area":null},{"id":"2405.13863","title":"Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning","created":"2024-05-22","cited_by_count":15,"area":"deeprl"},{"id":"2101.03238","title":"Neurosymbolic Transformers for Multi-Agent Communication","created":"2021-01-05","cited_by_count":13,"area":null},{"id":"2405.16450","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"1906.06717","title":"Mo\\\"ET: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning","created":"2019-06-16","cited_by_count":12,"area":"moe"},{"id":"2108.08454","title":"Improving Human Sequential Decision-Making with Reinforcement Learning","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2205.12449","title":"MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2202.02352","title":"Learning Interpretable, High-Performing Policies for Autonomous Driving","created":"2022-02-04","cited_by_count":11,"area":"driving"},{"id":"2203.11912","title":"What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategies","created":"2022-03-22","cited_by_count":11,"area":"offlinerl"},{"id":"2101.03263","title":"SyReNN: A Tool for Analyzing Deep Neural Networks","created":"2021-01-09","cited_by_count":10,"area":null},{"id":"2211.07882","title":"Explainable Action Advising for Multi-Agent Reinforcement Learning","created":"2022-11-15","cited_by_count":10,"area":"distill"},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2311.02104","title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2401.03188","title":"A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence","created":"2024-01-06","cited_by_count":10,"area":null},{"id":"1902.10657","title":"From explanation to synthesis: Compositional program induction for learning from demonstration","created":"2019-02-27","cited_by_count":9,"area":"offlinerl"},{"id":"2103.08228","title":"Learning Symbolic Rules for Interpretable Deep Reinforcement Learning","created":"2021-03-15","cited_by_count":9,"area":null},{"id":"2203.07671","title":"Safe Neurosymbolic Learning with Differentiable Symbolic Execution","created":"2022-03-15","cited_by_count":9,"area":null},{"id":"2212.14849","title":"Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search","created":"2022-12-30","cited_by_count":9,"area":null},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","cited_by_count":9,"area":null},{"id":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2107.13132","title":"Unsupervised Learning of Neurosymbolic Encoders","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2301.13185","title":"Optimal Decision Tree Policies for Markov Decision Processes","created":"2023-01-30","cited_by_count":8,"area":"offlinerl"},{"id":"2307.04893","title":"Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","cited_by_count":8,"area":"offlinerl"},{"id":"2508.05433","title":"Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies","created":"2025-08-07","cited_by_count":8,"area":"mllm"},{"id":"2508.19506","title":"Learning Game-Playing Agents with Generative Code Optimization","created":"2025-08-27","cited_by_count":8,"area":"agents"},{"id":"2211.01498","title":"On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2310.04327","title":"Program Synthesis with Best-First Bottom-Up Search","created":"2023-10-06","cited_by_count":7,"area":null},{"id":"2311.16018","title":"RIDE: Real-time Intrusion Detection via Explainable Machine Learning Implemented in a Memristor Hardware Architecture","created":"2023-11-27","cited_by_count":7,"area":null},{"id":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2105.07099","title":"Feature-Based Interpretable Reinforcement Learning based on State-Transition Models","created":"2021-05-14","cited_by_count":6,"area":null},{"id":"2112.03020","title":"Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2201.03698","title":"Verified Probabilistic Policies for Deep Reinforcement Learning","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2309.12701","title":"Breiman meets Bellman: Non-Greedy Decision Trees with MDPs","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2408.09135","title":"Vanilla Gradient Descent for Oblique Decision Trees","created":"2024-08-17","cited_by_count":6,"area":null},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2104.10219","title":"Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning","created":"2021-04-20","cited_by_count":5,"area":null},{"id":"2108.06898","title":"Neural-to-Tree Policy Distillation with Policy Improvement Criterion","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2202.03597","title":"Local Explanations for Reinforcement Learning","created":"2022-02-08","cited_by_count":5,"area":null},{"id":"2304.11526","title":"How to Control Hydrodynamic Force on Fluidic Pinball via Deep Reinforcement Learning","created":"2023-04-23","cited_by_count":5,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2309.03651","title":"Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments","created":"2023-09-07","cited_by_count":5,"area":null},{"id":"2403.00172","title":"Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control","created":"2024-02-29","cited_by_count":5,"area":"deeprl"},{"id":"2403.14328","title":"Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression","created":"2024-03-21","cited_by_count":5,"area":"deeprl"},{"id":"2405.05431","title":"Searching for Programmatic Policies in Semantic Spaces","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2407.15786","title":"LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning","created":"2024-07-22","cited_by_count":5,"area":"lr"},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2103.01203","title":"Generating Probabilistic Safety Guarantees for Neural Network Controllers","created":"2021-03-01","cited_by_count":4,"area":null},{"id":"2206.04266","title":"There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazes","created":"2022-06-09","cited_by_count":4,"area":null},{"id":"2211.03162","title":"ProtoX: Explaining a Reinforcement Learning Agent via Prototyping","created":"2022-11-06","cited_by_count":4,"area":null},{"id":"2405.15912","title":"Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2408.11632","title":"Optimizing Interpretable Decision Tree Policies for Reinforcement Learning","created":"2024-08-21","cited_by_count":4,"area":"offlinerl"},{"id":"2410.14371","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","cited_by_count":4,"area":"deeprl"},{"id":"2504.05625","title":"Model-Agnostic Policy Explanations with Large Language Models","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2104.10818","title":"XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees","created":"2021-04-22","cited_by_count":3,"area":null},{"id":"2106.06931","title":"Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning","created":"2021-06-13","cited_by_count":3,"area":null},{"id":"2109.06523","title":"Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking","created":"2021-09-14","cited_by_count":3,"area":null},{"id":"2110.13060","title":"Uniformly Conservative Exploration in Reinforcement Learning","created":"2021-10-25","cited_by_count":3,"area":null},{"id":"2112.06148","title":"Programming with Neural Surrogates of Programs","created":"2021-12-12","cited_by_count":3,"area":null},{"id":"2209.14148","title":"Guiding Safe Exploration with Weakest Preconditions","created":"2022-09-28","cited_by_count":3,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2308.02729","title":"Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks","created":"2023-08-04","cited_by_count":3,"area":null},{"id":"2309.10346","title":"Explaining Agent Behavior with Large Language Models","created":"2023-09-19","cited_by_count":3,"area":"agents"},{"id":"2311.06979","title":"Assessing the Interpretability of Programmatic Policies with Large Language Models","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2311.18062","title":"Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation","created":"2023-11-29","cited_by_count":3,"area":"agents"},{"id":"2406.03651","title":"Inductive Generalization in Reinforcement Learning from Specifications","created":"2024-06-05","cited_by_count":3,"area":"deeprl"},{"id":"2411.12173","title":"SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks","created":"2024-11-19","cited_by_count":3,"area":"deeprl"},{"id":"2412.13053","title":"SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks","created":"2024-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2503.08322","title":"Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs","created":"2025-03-11","cited_by_count":3,"area":"deeprl"},{"id":"2511.00116","title":"LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers","created":"2025-10-31","cited_by_count":3,"area":"agents"},{"id":"2104.13791","title":"Rule-based Shielding for Partially Observable Monte-Carlo Planning","created":"2021-04-28","cited_by_count":2,"area":null},{"id":"2201.07749","title":"Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction","created":"2022-01-17","cited_by_count":2,"area":null},{"id":"2210.01007","title":"Reward Learning with Trees: Methods and Evaluation","created":"2022-10-03","cited_by_count":2,"area":"alignment"},{"id":"2402.12685","title":"XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques","created":"2024-02-20","cited_by_count":2,"area":"deeprl"},{"id":"2402.13785","title":"Composing Reinforcement Learning Policies, with Formal Guarantees","created":"2024-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2408.04336","title":"KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination","created":"2024-08-08","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}