{"total":188,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2507.21053","title":"Flow Matching Policy Gradients","created":"2025-07-28","cited_by_count":99,"area":"diffusion"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43,"area":"offlinerl"},{"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":"2111.00072","title":"Generalized Proximal Policy Optimization with Sample Reuse","created":"2021-10-29","cited_by_count":40,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2105.01099","title":"Reinforcement Learning for Ridesharing: An Extended Survey","created":"2021-05-03","cited_by_count":35,"area":null},{"id":"2505.22257","title":"Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training","created":"2025-05-28","cited_by_count":34,"area":"lr"},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"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":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26,"area":"offlinerl"},{"id":"2406.00645","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning","created":"2024-06-02","cited_by_count":26,"area":"mllm"},{"id":"2105.11674","title":"Unbiased Asymmetric Reinforcement Learning under Partial Observability","created":"2021-05-25","cited_by_count":25,"area":null},{"id":"2203.14009","title":"Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey","created":"2022-03-26","cited_by_count":23,"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":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2407.20230","title":"SAPG: Split and Aggregate Policy Gradients","created":"2024-07-29","cited_by_count":21,"area":"deeprl"},{"id":"2109.01401","title":"CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models","created":"2021-09-03","cited_by_count":20,"area":null},{"id":"2112.13941","title":"Safe Reinforcement Learning with Chance-constrained Model Predictive Control","created":"2021-12-27","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":"2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","created":"2024-11-22","cited_by_count":18,"area":"deeprl"},{"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":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2302.12689","title":"GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations","created":"2023-02-24","cited_by_count":17,"area":null},{"id":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16,"area":null},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"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":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2109.06093","title":"Direct Advantage Estimation","created":"2021-09-13","cited_by_count":11,"area":null},{"id":"2207.08457","title":"A Meta-Reinforcement Learning Algorithm for Causal Discovery","created":"2022-07-18","cited_by_count":11,"area":null},{"id":"2211.17188","title":"Automated Play-Testing Through RL Based Human-Like Play-Styles Generation","created":"2022-11-29","cited_by_count":11,"area":null},{"id":"2305.18161","title":"VA-learning as a more efficient alternative to Q-learning","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2312.00342","title":"Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk","created":"2023-12-01","cited_by_count":11,"area":null},{"id":"2111.02202","title":"Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution","created":"2021-11-03","cited_by_count":10,"area":null},{"id":"2207.01566","title":"General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States","created":"2022-07-04","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":"2602.19362","title":"LLMs Can Learn to Reason Via Off-Policy RL","created":"2026-02-22","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":"2112.03798","title":"PTR-PPO: Proximal Policy Optimization with Prioritized Trajectory Replay","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2206.12848","title":"Analysis of Stochastic Processes through Replay Buffers","created":"2022-06-26","cited_by_count":9,"area":null},{"id":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2106.08832","title":"Solving Continuous Control with Episodic Memory","created":"2021-06-16","cited_by_count":8,"area":null},{"id":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8,"area":null},{"id":"2301.13289","title":"On the Statistical Benefits of Temporal Difference Learning","created":"2023-01-30","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":"2303.17615","title":"Utilizing Reinforcement Learning for de novo Drug Design","created":"2023-03-30","cited_by_count":7,"area":null},{"id":"2306.01276","title":"Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"id":"2102.10456","title":"Decaying Clipping Range in Proximal Policy Optimization","created":"2021-02-20","cited_by_count":6,"area":null},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2201.06126","title":"Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networks","created":"2022-01-16","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"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":"2301.11321","title":"Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2311.08290","title":"On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2102.04285","title":"RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads","created":"2021-02-08","cited_by_count":5,"area":null},{"id":"2102.05547","title":"Learning Equational Theorem Proving","created":"2021-02-10","cited_by_count":5,"area":"offlinerl"},{"id":"2109.14727","title":"Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2112.04213","title":"Convergence Results For Q-Learning With Experience Replay","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2210.01422","title":"Time-Varying Propensity Score to Bridge the Gap between the Past and Present","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2401.12455","title":"Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management","created":"2024-01-23","cited_by_count":5,"area":null},{"id":"2407.15537","title":"Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints","created":"2024-07-22","cited_by_count":5,"area":"deeprl"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2104.04004","title":"ACERAC: Efficient reinforcement learning in fine time discretization","created":"2021-04-08","cited_by_count":4,"area":null},{"id":"2202.06253","title":"Autonomous Drone Swarm Navigation and Multi-target Tracking in 3D Environments with Dynamic Obstacles","created":"2022-02-13","cited_by_count":4,"area":null},{"id":"2204.09315","title":"Learning to Constrain Policy Optimization with Virtual Trust Region","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2206.02544","title":"RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation","created":"2022-06-01","cited_by_count":4,"area":null},{"id":"2210.12448","title":"Probing Transfer in Deep Reinforcement Learning without Task Engineering","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2211.16221","title":"Configurable Agent With Reward As Input: A Play-Style Continuum Generation","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2310.11897","title":"Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning","created":"2023-10-18","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":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","cited_by_count":4,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2102.11319","title":"Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning","created":"2021-02-22","cited_by_count":3,"area":null},{"id":"2103.11265","title":"Bayesian Distributional Policy Gradients","created":"2021-03-20","cited_by_count":3,"area":null},{"id":"2107.05217","title":"Cautious Actor-Critic","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2108.04462","title":"Deep Reinforcement Learning for Demand Driven Services in Logistics and Transportation Systems: A Survey","created":"2021-08-10","cited_by_count":3,"area":null},{"id":"2109.07129","title":"What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation","created":"2021-09-15","cited_by_count":3,"area":null},{"id":"2110.02639","title":"On The Transferability of Deep-Q Networks","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2111.01865","title":"Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2112.01765","title":"Learning Emergent Random Access Protocol for LEO Satellite Networks","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2202.12162","title":"Measuring CLEVRness: Blackbox testing of Visual Reasoning Models","created":"2022-02-24","cited_by_count":3,"area":"lr"},{"id":"2204.11481","title":"\"Think Before You Speak\": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs","created":"2022-04-25","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":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2402.10374","title":"Revisiting Experience Replayable Conditions","created":"2024-02-15","cited_by_count":3,"area":"deeprl"},{"id":"2411.10268","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","created":"2024-11-15","cited_by_count":3,"area":"offlinerl"}],"next_cursor":"100"}