{"total":669,"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":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452,"area":"offlinerl"},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392,"area":null},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290,"area":null},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"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":"2101.03288","title":"How to Train Your Energy-Based Models","created":"2021-01-09","cited_by_count":274,"area":null},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251,"area":null},{"id":"2103.08050","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","created":"2021-03-14","cited_by_count":238,"area":"offlinerl"},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193,"area":"offlinerl"},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174,"area":null},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139,"area":"distill"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2408.08252","title":"Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding","created":"2024-08-15","cited_by_count":136,"area":"diffusion"},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132,"area":null},{"id":"2508.16153","title":"Memento: Fine-tuning LLM Agents without Fine-tuning LLMs","created":"2025-08-22","cited_by_count":127,"area":"agents"},{"id":"2410.13232","title":"Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation","created":"2024-10-17","cited_by_count":126,"area":"wm"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2202.01361","title":"Generative Flow Networks for Discrete Probabilistic Modeling","created":"2022-02-03","cited_by_count":114,"area":null},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112,"area":"diffusion"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104,"area":null},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101,"area":null},{"id":"2407.13734","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","created":"2024-07-18","cited_by_count":98,"area":"diffusion"},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2405.15177","title":"Diffusion Actor-Critic with Entropy Regulator","created":"2024-05-24","cited_by_count":94,"area":"diffusion"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85,"area":"offlinerl"},{"id":"2302.01687","title":"Better Training of GFlowNets with Local Credit and Incomplete Trajectories","created":"2023-02-03","cited_by_count":85,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"area":"alignment"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"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":"2502.00361","title":"Efficient Online Reinforcement Learning for Diffusion Policy","created":"2025-02-01","cited_by_count":71,"area":"diffusion"},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69,"area":"offlinerl"},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67,"area":null},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63,"area":null},{"id":"2104.03086","title":"Trajectory Prediction with Latent Belief Energy-Based Model","created":"2021-04-07","cited_by_count":60,"area":null},{"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":"2502.02316","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","created":"2025-02-04","cited_by_count":58,"area":"diffusion"},{"id":"2106.03498","title":"Identifiability in inverse reinforcement learning","created":"2021-06-07","cited_by_count":55,"area":"offlinerl"},{"id":"2006.14154","title":"Strictly Batch Imitation Learning by Energy-based Distribution Matching","created":"2020-06-25","cited_by_count":54,"area":"offlinerl"},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"area":"lr"},{"id":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","cited_by_count":53,"area":null},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2210.03308","title":"Generative Augmented Flow Networks","created":"2022-10-07","cited_by_count":50,"area":null},{"id":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50,"area":"deeprl"},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2308.08758","title":"Discrete Prompt Compression with Reinforcement Learning","created":"2023-08-17","cited_by_count":42,"area":"inference"},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2004.09395","title":"Energy-Based Imitation Learning","created":"2020-04-20","cited_by_count":40,"area":"offlinerl"},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40,"area":"offlinerl"},{"id":"2305.17010","title":"Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets","created":"2023-05-26","cited_by_count":40,"area":null},{"id":"2103.07927","title":"Modelling Behavioural Diversity for Learning in Open-Ended Games","created":"2021-03-14","cited_by_count":39,"area":null},{"id":"2109.07719","title":"Efficient Differentiable Simulation of Articulated Bodies","created":"2021-09-16","cited_by_count":39,"area":null},{"id":"2205.01758","title":"Differentiable Simulation of Soft Multi-body Systems","created":"2022-05-03","cited_by_count":39,"area":null},{"id":"2402.05961","title":"Genetic-guided GFlowNets for Sample Efficient Molecular Optimization","created":"2024-02-05","cited_by_count":39,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2112.09559","title":"ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms","created":"2021-12-17","cited_by_count":35,"area":null},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34,"area":null},{"id":"2502.11612","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy","created":"2025-02-17","cited_by_count":34,"area":"diffusion"},{"id":"2506.20701","title":"Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models","created":"2025-06-25","cited_by_count":34,"area":"diffusion"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2302.09465","title":"Stochastic Generative Flow Networks","created":"2023-02-19","cited_by_count":32,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2412.07775","title":"Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets","created":"2024-12-10","cited_by_count":32,"area":"diffusion"},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"area":null},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2402.04080","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","created":"2024-02-06","cited_by_count":31,"area":"diffusion"},{"id":"2312.14331","title":"Maximum entropy GFlowNets with soft Q-learning","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2410.17215","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","created":"2024-10-22","cited_by_count":29,"area":"distill"},{"id":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"1905.11108","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","created":"2019-05-27","cited_by_count":28,"area":"offlinerl"},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"area":null}],"next_cursor":"100"}