{"total":264,"rows":[{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372,"area":null},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"area":"offlinerl"},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73,"area":null},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2410.14803","title":"DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents","created":"2024-10-18","cited_by_count":68,"area":"lr"},{"id":"2506.00613","title":"WorldGym: World Model as An Environment for Policy Evaluation","created":"2025-05-31","cited_by_count":64,"area":"wm"},{"id":"2503.14286","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","created":"2025-03-18","cited_by_count":61,"area":null},{"id":"2102.01567","title":"A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants","created":"2021-02-02","cited_by_count":57,"area":null},{"id":"2406.11827","title":"WPO: Enhancing RLHF with Weighted Preference Optimization","created":"2024-06-17","cited_by_count":54,"area":"alignment"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2106.11144","title":"Scientific multi-agent reinforcement learning for wall-models of turbulent flows","created":"2021-06-21","cited_by_count":52,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2312.02027","title":"Stochastic Optimal Control Matching","created":"2023-12-04","cited_by_count":40,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2601.08521","title":"Your Group-Relative Advantage Is Biased","created":"2026-01-13","cited_by_count":34,"area":"lr"},{"id":"2112.02845","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","created":"2021-12-06","cited_by_count":32,"area":"offlinerl"},{"id":"2509.19128","title":"PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation","created":"2025-09-23","cited_by_count":32,"area":"lr"},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2512.24873","title":"Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem","created":"2025-12-31","cited_by_count":30,"area":"agents"},{"id":"2506.20520","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","created":"2025-06-25","cited_by_count":29,"area":"lr"},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2201.11861","title":"The Challenges of Exploration for Offline Reinforcement Learning","created":"2022-01-27","cited_by_count":26,"area":"offlinerl"},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2103.07084","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","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":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"area":null},{"id":"2503.03660","title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns","created":"2025-03-05","cited_by_count":16,"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":"2104.06521","title":"TAAC: Temporally Abstract Actor-Critic for Continuous Control","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2401.00364","title":"Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise","created":"2023-12-31","cited_by_count":15,"area":null},{"id":"2510.11345","title":"Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony","created":"2025-10-13","cited_by_count":15,"area":"agents"},{"id":"2106.14979","title":"On component interactions in two-stage recommender systems","created":"2021-06-28","cited_by_count":14,"area":null},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2305.05239","title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","created":"2023-05-09","cited_by_count":14,"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":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13,"area":"offlinerl"},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2002.06473","title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","created":"2020-02-15","cited_by_count":12,"area":"offlinerl"},{"id":"2105.14900","title":"A unified view of likelihood ratio and reparameterization gradients","created":"2021-05-31","cited_by_count":12,"area":null},{"id":"2112.04145","title":"A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions","created":"2021-12-08","cited_by_count":12,"area":null},{"id":"2204.03084","title":"Knowledge Infused Decoding","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2109.06093","title":"Direct Advantage Estimation","created":"2021-09-13","cited_by_count":11,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2102.01985","title":"Variance Penalized On-Policy and Off-Policy Actor-Critic","created":"2021-02-03","cited_by_count":10,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2207.07570","title":"The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning","created":"2022-07-15","cited_by_count":10,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2302.09339","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","created":"2023-02-18","cited_by_count":10,"area":null},{"id":"2303.04096","title":"Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2602.19362","title":"LLMs Can Learn to Reason Via Off-Policy RL","created":"2026-02-22","cited_by_count":10,"area":"lr"},{"id":"2603.06743","title":"Stabilizing Reinforcement Learning for Diffusion Language Models","created":"2026-03-06","cited_by_count":10,"area":"lr"},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2402.03903","title":"Averaging $n$-step Returns Reduces Variance in Reinforcement Learning","created":"2024-02-06","cited_by_count":9,"area":"deeprl"},{"id":"2405.20860","title":"Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation","created":"2024-05-31","cited_by_count":9,"area":"deeprl"},{"id":"2507.02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","created":"2025-07-03","cited_by_count":9,"area":"deeprl"},{"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":"2604.08706","title":"Efficient RL Training for LLMs with Experience Replay","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2111.03474","title":"Supervised Advantage Actor-Critic for Recommender Systems","created":"2021-11-05","cited_by_count":8,"area":null},{"id":"2402.12874","title":"Skill or Luck? Return Decomposition via Advantage Functions","created":"2024-02-20","cited_by_count":8,"area":"deeprl"},{"id":"2511.07730","title":"Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning","created":"2025-11-11","cited_by_count":8,"area":"deeprl"},{"id":"2106.00707","title":"An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2106.06232","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2108.08485","title":"Language Model Augmented Relevance Score","created":"2021-08-19","cited_by_count":7,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2405.11206","title":"Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses","created":"2024-05-18","cited_by_count":7,"area":"offlinerl"},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2511.11828","title":"Conformal Constrained Policy Optimization for Cost-Effective LLM Agents","created":"2025-11-14","cited_by_count":7,"area":"agents"}],"next_cursor":"100"}