{"total":115,"rows":[{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"id":"2310.15145","title":"Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning","created":"2023-10-23","cited_by_count":54,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2107.08981","title":"Hierarchical Few-Shot Imitation with Skill Transition Models","created":"2021-07-19","cited_by_count":37,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2104.02293","title":"On the Optimality of Batch Policy Optimization Algorithms","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2206.10524","title":"Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control","created":"2022-06-21","cited_by_count":28,"area":null},{"id":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24,"area":null},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2302.09772","title":"Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot","created":"2023-02-20","cited_by_count":23,"area":null},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22,"area":null},{"id":"2106.03050","title":"Efficient Continuous Control with Double Actors and Regularized Critics","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2211.11802","title":"Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning","created":"2022-11-21","cited_by_count":20,"area":null},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"2405.05349","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2110.04507","title":"TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations","created":"2021-10-09","cited_by_count":18,"area":null},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18,"area":null},{"id":"2211.09019","title":"Learning Reward Functions for Robotic Manipulation by Observing Humans","created":"2022-11-16","cited_by_count":17,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2301.12012","title":"In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States","created":"2023-01-27","cited_by_count":16,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2310.10735","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2310.19308","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning","created":"2023-10-30","cited_by_count":13,"area":null},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2401.05442","title":"Functional Graphical Models: Structure Enables Offline Data-Driven Optimization","created":"2024-01-08","cited_by_count":11,"area":null},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2208.02294","title":"Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2306.06253","title":"Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2301.02220","title":"Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2204.12750","title":"DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games","created":"2022-04-27","cited_by_count":6,"area":null},{"id":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2209.09174","title":"Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2210.08153","title":"CUP: Critic-Guided Policy Reuse","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","created":"2022-11-24","cited_by_count":6,"area":null},{"id":"2204.05893","title":"Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2211.13337","title":"Multi-Environment Pretraining Enables Transfer to Action Limited Datasets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2312.15863","title":"PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2404.15084","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2102.11448","title":"MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning","created":"2021-02-23","cited_by_count":4,"area":null},{"id":"2304.00354","title":"On Context Distribution Shift in Task Representation Learning for Offline Meta RL","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2404.10017","title":"Model-based Offline Quantum Reinforcement Learning","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2605.02141","title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2201.08115","title":"Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning","created":"2022-01-20","cited_by_count":3,"area":null},{"id":"2203.04303","title":"Policy Regularization for Legible Behavior","created":"2022-03-08","cited_by_count":3,"area":null},{"id":"2209.00876","title":"Dialogue Evaluation with Offline Reinforcement Learning","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2307.13101","title":"Contrastive Example-Based Control","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2605.07727","title":"Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.26552","title":"Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2303.02234","title":"Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2303.10828","title":"DataLight: Offline Data-Driven Traffic Signal Control","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2303.16469","title":"Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2305.11340","title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models","created":"2023-05-18","cited_by_count":2,"area":null},{"id":"2311.03651","title":"SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2502.15345","title":"Efficiently Solving Discounted MDPs with Predictions on Transition Matrices","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2601.20116","title":"In-Context Reinforcement Learning From Suboptimal Historical Data","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2605.18580","title":"When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State","created":"2026-05-18","cited_by_count":2,"area":null},{"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":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2206.13714","title":"Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse","created":"2022-06-28","cited_by_count":1,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2312.02308","title":"AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2408.07753","title":"How to Solve Contextual Goal-Oriented Problems with Offline Datasets?","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2504.17277","title":"ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2603.00374","title":"Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2605.06529","title":"Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.27877","title":"SPAR: Support-Preserving Action Rectification","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.27475","title":"Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2109.09037","title":"Dual Behavior Regularized Reinforcement Learning","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2206.06009","title":"Relative Policy-Transition Optimization for Fast Policy Transfer","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2208.02362","title":"Bayesian regularization of empirical MDPs","created":"2022-08-03","cited_by_count":0,"area":null},{"id":"2208.10533","title":"Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2304.00573","title":"Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning","created":"2023-04-02","cited_by_count":0,"area":null},{"id":"2306.14297","title":"Inference for relative sparsity","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2307.04927","title":"Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)","created":"2023-07-10","cited_by_count":0,"area":null}],"next_cursor":"100"}