{"total":138,"rows":[{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500,"area":"alignment"},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305,"area":"offlinerl"},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125,"area":"offlinerl"},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2507.14805","title":"Subliminal Learning: Language models transmit behavioral traits via hidden signals in data","created":"2025-07-20","cited_by_count":95,"area":null},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89,"area":"offlinerl"},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72,"area":null},{"id":"2110.01219","title":"Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation","created":"2021-10-04","cited_by_count":68,"area":null},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61,"area":null},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2509.19301","title":"Residual Off-Policy RL for Finetuning Behavior Cloning Policies","created":"2025-09-23","cited_by_count":55,"area":null},{"id":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51,"area":"offlinerl"},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2307.09668","title":"Towards A Unified Agent with Foundation Models","created":"2023-07-18","cited_by_count":47,"area":"mllm"},{"id":"2506.12811","title":"Flow-Based Policy for Online Reinforcement Learning","created":"2025-06-15","cited_by_count":37,"area":"deeprl"},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2103.13834","title":"Self-Imitation Learning by Planning","created":"2021-03-25","cited_by_count":26,"area":"offlinerl"},{"id":"1812.00950","title":"Generative Adversarial Self-Imitation Learning","created":"2018-12-03","cited_by_count":25,"area":"offlinerl"},{"id":"2206.03378","title":"Imitating Past Successes can be Very Suboptimal","created":"2022-06-07","cited_by_count":23,"area":"offlinerl"},{"id":"2201.01251","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games","created":"2022-01-04","cited_by_count":22,"area":null},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22,"area":null},{"id":"2210.09241","title":"Boosting Offline Reinforcement Learning via Data Rebalancing","created":"2022-10-17","cited_by_count":22,"area":"offlinerl"},{"id":"2212.09246","title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation","created":"2022-12-19","cited_by_count":21,"area":"distill"},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2103.11883","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","created":"2021-03-22","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":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2203.02107","title":"Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrations","created":"2022-03-04","cited_by_count":15,"area":"offlinerl"},{"id":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13,"area":"offlinerl"},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"area":"offlinerl"},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2211.15823","title":"Personalized Reward Learning with Interaction-Grounded Learning (IGL)","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2307.16503","title":"Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot","created":"2023-07-31","cited_by_count":9,"area":null},{"id":"2412.15534","title":"SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch","created":"2024-12-20","cited_by_count":9,"area":"offlinerl"},{"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":"1909.11468","title":"Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems","created":"2019-09-25","cited_by_count":7,"area":"offlinerl"},{"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":"2405.03064","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","created":"2024-05-05","cited_by_count":7,"area":"deeprl"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"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":"2212.02064","title":"E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"2312.03446","title":"Visual Hindsight Self-Imitation Learning for Interactive Navigation","created":"2023-12-05","cited_by_count":6,"area":"offlinerl"},{"id":"2102.05547","title":"Learning Equational Theorem Proving","created":"2021-02-10","cited_by_count":5,"area":"offlinerl"},{"id":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2206.00233","title":"DM$^2$: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2207.09071","title":"Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks","created":"2022-07-19","cited_by_count":5,"area":null},{"id":"2212.10765","title":"Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search","created":"2022-12-21","cited_by_count":5,"area":null},{"id":"2305.01868","title":"Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2402.03357","title":"Harnessing Network Effect for Fake News Mitigation: Selecting Debunkers via Self-Imitation Learning","created":"2024-01-28","cited_by_count":5,"area":null},{"id":"2407.20798","title":"Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning","created":"2024-07-30","cited_by_count":5,"area":"mllm"},{"id":"2408.09974","title":"The Exploration-Exploitation Dilemma Revisited: An Entropy Perspective","created":"2024-08-19","cited_by_count":5,"area":"deeprl"},{"id":"2109.13498","title":"Learning to Superoptimize Real-world Programs","created":"2021-09-28","cited_by_count":4,"area":null},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4,"area":"offlinerl"},{"id":"2210.05845","title":"Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2306.06754","title":"Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning","created":"2023-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2311.01953","title":"Optimistic Multi-Agent Policy Gradient","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2501.15034","title":"Divergence-Augmented Policy Optimization","created":"2025-01-25","cited_by_count":4,"area":"deeprl"},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2112.07342","title":"Learning to Guide and to Be Guided in the Architect-Builder Problem","created":"2021-12-14","cited_by_count":3,"area":null},{"id":"2302.02299","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","created":"2023-02-05","cited_by_count":3,"area":null},{"id":"2303.09367","title":"Goal-conditioned Offline Reinforcement Learning through State Space Partitioning","created":"2023-03-16","cited_by_count":3,"area":"offlinerl"},{"id":"2306.15503","title":"Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning","created":"2023-06-27","cited_by_count":3,"area":"offlinerl"},{"id":"2402.04539","title":"Learning Diverse Policies with Soft Self-Generated Guidance","created":"2024-02-07","cited_by_count":3,"area":"deeprl"},{"id":"2410.04855","title":"Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2410.16128","title":"SMART: Self-learning Meta-strategy Agent for Reasoning Tasks","created":"2024-10-21","cited_by_count":3,"area":"lr"},{"id":"2508.06108","title":"GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning","created":"2025-08-08","cited_by_count":3,"area":"deeprl"},{"id":"2510.10181","title":"Dejavu: Towards Experience Feedback Learning for Embodied Intelligence","created":"2025-10-11","cited_by_count":3,"area":null},{"id":"2605.29563","title":"Planning with the Views","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2312.16456","title":"Adaptive trajectory-constrained exploration strategy for deep reinforcement learning","created":"2023-12-27","cited_by_count":2,"area":null},{"id":"2404.03997","title":"Demonstration Guided Multi-Objective Reinforcement Learning","created":"2024-04-05","cited_by_count":2,"area":"deeprl"},{"id":"2409.02724","title":"Surgical Task Automation Using Actor-Critic Frameworks and Self-Supervised Imitation Learning","created":"2024-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2410.14957","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","created":"2024-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2410.22524","title":"Hindsight Experience Replay Accelerates Proximal Policy Optimization","created":"2024-10-29","cited_by_count":2,"area":"deeprl"},{"id":"2509.10504","title":"Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2601.22965","title":"Self-Imitated Diffusion Policy for Efficient and Robust Visual Navigation","created":"2026-01-30","cited_by_count":2,"area":"diffusion"},{"id":"2606.06219","title":"CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving","created":"2026-06-04","cited_by_count":2,"area":"driving"},{"id":"2607.19749","title":"The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL","created":"2026-07-22","cited_by_count":2,"area":"wm"},{"id":"2102.03138","title":"An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios","created":"2021-02-05","cited_by_count":1,"area":null},{"id":"2201.03834","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","created":"2022-01-11","cited_by_count":1,"area":"offlinerl"},{"id":"2212.03562","title":"Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble","created":"2022-12-07","cited_by_count":1,"area":"offlinerl"},{"id":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2401.02225","title":"Trajectory-Oriented Policy Optimization with Sparse Rewards","created":"2024-01-04","cited_by_count":1,"area":"deeprl"},{"id":"2406.13223","title":"Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Driving","created":"2024-06-19","cited_by_count":1,"area":"driving"}],"next_cursor":"100"}