{"total":55,"rows":[{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"area":null},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30,"area":null},{"id":"2110.11960","title":"ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models","created":"2021-10-22","cited_by_count":25,"area":null},{"id":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24,"area":null},{"id":"2412.11120","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","created":"2024-12-15","cited_by_count":23,"area":null},{"id":"2305.18427","title":"Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach","created":"2023-05-28","cited_by_count":19,"area":null},{"id":"2309.12482","title":"State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding","created":"2023-09-21","cited_by_count":17,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2401.00298","title":"Principal-Agent Reward Shaping in MDPs","created":"2023-12-30","cited_by_count":13,"area":null},{"id":"2112.15400","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","created":"2021-12-31","cited_by_count":12,"area":null},{"id":"2209.14271","title":"Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2103.09159","title":"Learning to Shape Rewards using a Game of Two Partners","created":"2021-03-16","cited_by_count":9,"area":null},{"id":"2407.16186","title":"Automatic Environment Shaping is the Next Frontier in RL","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2202.02790","title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning","created":"2022-02-06","cited_by_count":6,"area":null},{"id":"2111.01919","title":"Discovering and Exploiting Sparse Rewards in a Learned Behavior Space","created":"2021-11-02","cited_by_count":5,"area":null},{"id":"2210.03455","title":"Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2310.17785","title":"Learning Extrinsic Dexterity with Parameterized Manipulation Primitives","created":"2023-10-26","cited_by_count":5,"area":null},{"id":"2311.10026","title":"Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2112.11217","title":"Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles","created":"2021-12-18","cited_by_count":4,"area":null},{"id":"2302.03429","title":"Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2208.02680","title":"Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations","created":"2022-08-04","cited_by_count":3,"area":null},{"id":"2209.09648","title":"Safe Reinforcement Learning with Contrastive Risk Prediction","created":"2022-09-10","cited_by_count":3,"area":null},{"id":"2303.03787","title":"Sample-efficient Real-time Planning with Curiosity Cross-Entropy Method and Contrastive Learning","created":"2023-03-07","cited_by_count":3,"area":null},{"id":"2309.02632","title":"Deep Reinforcement Learning from Hierarchical Preference Design","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2502.14096","title":"Aligned Multi Objective Optimization","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2505.07854","title":"CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2111.04865","title":"On Assessing The Safety of Reinforcement Learning algorithms Using Formal Methods","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2312.15160","title":"Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning","created":"2023-12-23","cited_by_count":2,"area":null},{"id":"2405.03341","title":"Enhancing Q-Learning with Large Language Model Heuristics","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2605.28918","title":"When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2102.03866","title":"Model-Augmented Q-learning","created":"2021-02-07","cited_by_count":1,"area":null},{"id":"2306.08224","title":"Expanding Versatility of Agile Locomotion through Policy Transitions Using Latent State Representation","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2309.16164","title":"Learning to Terminate in Object Navigation","created":"2023-09-28","cited_by_count":1,"area":null},{"id":"2311.16339","title":"Reward Shaping for Improved Learning in Real-time Strategy Game Play","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2401.06771","title":"Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Design","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2506.20059","title":"DiaLLMs: EHR Enhanced Clinical Conversational System for Clinical Test Recommendation and Diagnosis Prediction","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2202.02918","title":"Soft Actor-Critic with Inhibitory Networks for Faster Retraining","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2211.07941","title":"Automatic Evaluation of Excavator Operators using Learned Reward Functions","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2211.16691","title":"Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules","created":"2022-11-30","cited_by_count":0,"area":null},{"id":"2304.02738","title":"Core Challenges in Embodied Vision-Language Planning","created":"2023-04-05","cited_by_count":0,"area":null},{"id":"2304.07163","title":"Bandit-Based Policy Invariant Explicit Shaping for Incorporating External Advice in Reinforcement Learning","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2307.04841","title":"Loss Dynamics of Temporal Difference Reinforcement Learning","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2309.02869","title":"On Reducing Undesirable Behavior in Deep Reinforcement Learning Models","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2501.10938","title":"Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning","created":"2025-01-19","cited_by_count":0,"area":null},{"id":"2503.21640","title":"Towards Fully Automated Decision-Making Systems for Greenhouse Control: Challenges and Opportunities","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2510.20408","title":"Balancing Specialization and Centralization: A Multi-Agent Reinforcement Learning Benchmark for Sequential Industrial Control","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2603.02680","title":"LLMs for High-Frequency Decision-Making: Normalized Action Reward-Guided Consistency Policy Optimization","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2606.20236","title":"A Multi-Agent system for Multi-Objective constrained optimization","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.09422","title":"Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.13566","title":"Planning or Learning: Reliability and Cost in Multi-Asset Maintenance","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}