{"total":173,"rows":[{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223,"area":"diffusion"},{"id":"2408.08152","title":"DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search","created":"2024-08-15","cited_by_count":197,"area":"lr"},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2509.03312","title":"AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?","created":"2025-09-03","cited_by_count":116,"area":"agents"},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79,"area":"agents"},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"1810.11748","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","created":"2018-10-28","cited_by_count":41,"area":"alignment"},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"area":"agents"},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40,"area":"offlinerl"},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38,"area":"wm"},{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2607.14777","title":"SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning","created":"2026-07-16","cited_by_count":32,"area":"agents"},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2111.04714","title":"A Dataset Perspective on Offline Reinforcement Learning","created":"2021-11-08","cited_by_count":27,"area":"offlinerl"},{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25,"area":null},{"id":"2310.03301","title":"Learning Energy Decompositions for Partial Inference of GFlowNets","created":"2023-10-05","cited_by_count":24,"area":null},{"id":"2603.22293","title":"TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs","created":"2026-03-11","cited_by_count":24,"area":null},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"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":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2402.00854","title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","created":"2024-02-01","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2111.02104","title":"Model-Based Episodic Memory Induces Dynamic Hybrid Controls","created":"2021-11-03","cited_by_count":14,"area":null},{"id":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12,"area":"alignment"},{"id":"2608.05987","title":"AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning","created":"2026-08-06","cited_by_count":12,"area":"agents"},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2402.05290","title":"Do Transformer World Models Give Better Policy Gradients?","created":"2024-02-07","cited_by_count":10,"area":"wm"},{"id":"2411.08302","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","created":"2024-11-13","cited_by_count":10,"area":"alignment"},{"id":"2606.11119","title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","created":"2026-06-09","cited_by_count":10,"area":"agents"},{"id":"2201.04612","title":"Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2203.11526","title":"Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2207.05742","title":"Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning","created":"2022-07-12","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":"2410.05656","title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making","created":"2024-10-08","cited_by_count":9,"area":"alignment"},{"id":"2511.20718","title":"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2111.05884","title":"Search in Imperfect Information Games","created":"2021-11-10","cited_by_count":8,"area":null},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2302.00237","title":"Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)","created":"2023-02-01","cited_by_count":7,"area":null},{"id":"2411.00722","title":"Token-level Proximal Policy Optimization for Query Generation","created":"2024-11-01","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2210.17540","title":"Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2303.02646","title":"Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation","created":"2023-03-05","cited_by_count":6,"area":"offlinerl"},{"id":"2306.03293","title":"Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2310.07123","title":"Off-Policy Evaluation for Human Feedback","created":"2023-10-11","cited_by_count":6,"area":"alignment"},{"id":"2312.11364","title":"Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2503.03796","title":"Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm","created":"2025-03-05","cited_by_count":6,"area":"agents"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2606.00593","title":"SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering","created":"2026-05-30","cited_by_count":6,"area":null},{"id":"2106.04499","title":"Towards Practical Credit Assignment for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2209.03798","title":"ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques","created":"2022-09-08","cited_by_count":5,"area":null},{"id":"2304.07520","title":"STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2609.04094","title":"DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training","created":"2026-09-03","cited_by_count":5,"area":null},{"id":"2202.09699","title":"Selective Credit Assignment","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2409.04744","title":"Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2410.15184","title":"Action abstractions for amortized sampling","created":"2024-10-19","cited_by_count":4,"area":"deeprl"},{"id":"2606.07367","title":"Self-evolving LLM agents with in-distribution Optimization","created":"2026-06-05","cited_by_count":4,"area":"agents"},{"id":"2608.09263","title":"Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":4,"area":"distill"},{"id":"2608.31077","title":"Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization","created":"2026-08-31","cited_by_count":4,"area":"agents"},{"id":"2106.05332","title":"Reinforcement Learning for Industrial Control Network Cyber Security Orchestration","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2307.04098","title":"A User Study on Explainable Online Reinforcement Learning for Adaptive Systems","created":"2023-07-09","cited_by_count":3,"area":null},{"id":"2402.07019","title":"Informativeness of Reward Functions in Reinforcement Learning","created":"2024-02-10","cited_by_count":3,"area":"deeprl"},{"id":"2407.00115","title":"Instance Temperature Knowledge Distillation","created":"2024-06-27","cited_by_count":3,"area":"distill"},{"id":"2605.09287","title":"PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning","created":"2026-05-10","cited_by_count":3,"area":"agents"},{"id":"2605.27788","title":"Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2607.22832","title":"MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution","created":"2026-07-24","cited_by_count":3,"area":null},{"id":"2102.04999","title":"Adaptive Pairwise Weights for Temporal Credit Assignment","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2202.10464","title":"A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2303.13660","title":"Presenting Multiagent Challenges in Team Sports Analytics","created":"2023-03-23","cited_by_count":2,"area":null},{"id":"2306.16205","title":"Towards a Better Understanding of Learning with Multiagent Teams","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2312.10642","title":"Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward","created":"2023-12-17","cited_by_count":2,"area":null},{"id":"2405.18289","title":"Highway Reinforcement Learning","created":"2024-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2410.20176","title":"Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning","created":"2024-10-26","cited_by_count":2,"area":"alignment"},{"id":"2411.09176","title":"Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2505.15922","title":"Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition","created":"2025-05-21","cited_by_count":2,"area":"agents"},{"id":"2506.06410","title":"Delphos: A reinforcement learning framework for assisting discrete choice model specification","created":"2025-06-06","cited_by_count":2,"area":"deeprl"},{"id":"2509.21828","title":"Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2025-09-26","cited_by_count":2,"area":"agents"},{"id":"2606.04889","title":"GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2606.12916","title":"MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2608.06861","title":"Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents","created":"2026-08-07","cited_by_count":2,"area":"agents"},{"id":"2608.21027","title":"Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2609.12424","title":"Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement Learning","created":"2026-09-11","cited_by_count":2,"area":"agents"},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2111.02445","title":"Autonomous Attack Mitigation for Industrial Control Systems","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2201.05464","title":"Bayesian sense of time in biological and artificial brains","created":"2022-01-14","cited_by_count":1,"area":null}],"next_cursor":"100"}