{"total":2258,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191,"area":"agents"},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251,"area":"agents"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662,"area":"offlinerl"},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508,"area":"wm"},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500,"area":"alignment"},{"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":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397,"area":"wm"},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396,"area":"alignment"},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372,"area":null},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350,"area":"lr"},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302,"area":"alignment"},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300,"area":"wm"},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271,"area":null},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251,"area":null},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229,"area":"alignment"},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196,"area":"alignment"},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194,"area":"driving"},{"id":"2202.11742","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","created":"2022-02-23","cited_by_count":193,"area":null},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"area":null},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"area":"alignment"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2311.13743","title":"FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design","created":"2023-11-23","cited_by_count":164,"area":"agents"},{"id":"2211.07638","title":"Legged Locomotion in Challenging Terrains using Egocentric Vision","created":"2022-11-14","cited_by_count":151,"area":null},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"area":null},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139,"area":"wm"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"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":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2402.10571","title":"Direct Preference Optimization with an Offset","created":"2024-02-16","cited_by_count":122,"area":"alignment"},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119,"area":null},{"id":"2211.07089","title":"PMR: Prototypical Modal Rebalance for Multimodal Learning","created":"2022-11-14","cited_by_count":116,"area":null},{"id":"2409.14393","title":"MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting","created":"2024-09-22","cited_by_count":116,"area":null},{"id":"2407.06567","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","created":"2024-07-09","cited_by_count":113,"area":"agents"},{"id":"2308.02151","title":"Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization","created":"2023-08-04","cited_by_count":112,"area":"agents"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2405.16173","title":"Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization","created":"2024-05-25","cited_by_count":110,"area":"diffusion"},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108,"area":null},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104,"area":null},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102,"area":null},{"id":"2111.11232","title":"Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms","created":"2021-11-22","cited_by_count":101,"area":null},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2304.13972","title":"Convergence of Adam Under Relaxed Assumptions","created":"2023-04-27","cited_by_count":99,"area":null},{"id":"2507.21053","title":"Flow Matching Policy Gradients","created":"2025-07-28","cited_by_count":99,"area":"diffusion"},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97,"area":null},{"id":"2308.10916","title":"Diffusion Model as Representation Learner","created":"2023-08-21","cited_by_count":95,"area":"diffusion"},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2402.19464","title":"Curiosity-driven Red-teaming for Large Language Models","created":"2024-02-29","cited_by_count":88,"area":"safety"},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87,"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":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80,"area":"alignment"},{"id":"2108.06325","title":"Continual Backprop: Stochastic Gradient Descent with Persistent Randomness","created":"2021-08-13","cited_by_count":80,"area":null},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"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":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73,"area":"alignment"},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72,"area":"alignment"},{"id":"2102.08607","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","created":"2021-02-17","cited_by_count":70,"area":null},{"id":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70,"area":null},{"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}],"next_cursor":"100"}