{"total":328,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662,"area":"offlinerl"},{"id":"2511.14759","title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","created":"2025-11-18","cited_by_count":303,"area":"vla"},{"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":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215,"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":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2406.04151","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","created":"2024-06-06","cited_by_count":120,"area":"agents"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112,"area":"offlinerl"},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111,"area":"agents"},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"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":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79,"area":"offlinerl"},{"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":"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":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"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":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2407.00993","title":"Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents","created":"2024-07-01","cited_by_count":56,"area":"agents"},{"id":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2411.04282","title":"Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding","created":"2024-11-06","cited_by_count":55,"area":"lr"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2604.23073","title":"RL Token: Bootstrapping Online RL with Vision-Language-Action Models","created":"2026-04-24","cited_by_count":49,"area":"vla"},{"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":"2412.02617","title":"Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback","created":"2024-12-03","cited_by_count":47,"area":"mllm"},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2210.04932","title":"NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields","created":"2022-10-10","cited_by_count":44,"area":null},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43,"area":null},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"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":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41,"area":"offlinerl"},{"id":"2102.11938","title":"Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others","created":"2021-02-23","cited_by_count":39,"area":null},{"id":"2310.06343","title":"Boosting Continuous Control with Consistency Policy","created":"2023-10-10","cited_by_count":38,"area":"diffusion"},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38,"area":"lr"},{"id":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35,"area":null},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34,"area":"lr"},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31,"area":"offlinerl"},{"id":"2402.05546","title":"Offline Actor-Critic Reinforcement Learning Scales to Large Models","created":"2024-02-08","cited_by_count":30,"area":"offlinerl"},{"id":"2206.00484","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","created":"2022-05-30","cited_by_count":29,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2103.04909","title":"Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing","created":"2021-03-08","cited_by_count":26,"area":"wm"},{"id":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","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":"2303.17396","title":"Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions","created":"2023-03-30","cited_by_count":26,"area":"offlinerl"},{"id":"2405.13629","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","created":"2024-05-22","cited_by_count":26,"area":"deeprl"},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"},{"id":"2101.09207","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","created":"2021-01-22","cited_by_count":25,"area":null},{"id":"2106.09119","title":"Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL","created":"2021-06-16","cited_by_count":24,"area":"offlinerl"},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2305.10912","title":"A Generalist Dynamics Model for Control","created":"2023-05-18","cited_by_count":24,"area":"wm"},{"id":"2407.14503","title":"Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification","created":"2024-07-19","cited_by_count":23,"area":"alignment"},{"id":"2508.12511","title":"Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference","created":"2025-08-17","cited_by_count":23,"area":null},{"id":"2102.13176","title":"A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2109.14311","title":"Learning Dynamics Models for Model Predictive Agents","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2203.04051","title":"Robot Learning of Mobile Manipulation with Reachability Behavior Priors","created":"2022-03-08","cited_by_count":22,"area":null},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","cited_by_count":20,"area":"offlinerl"},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2405.00987","title":"S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic","created":"2024-05-02","cited_by_count":18,"area":"deeprl"},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2405.02425","title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":17,"area":"deeprl"},{"id":"2510.07475","title":"MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference","created":"2025-10-08","cited_by_count":17,"area":"agents"},{"id":"2205.15460","title":"Critic Sequential Monte Carlo","created":"2022-05-30","cited_by_count":16,"area":null},{"id":"2301.11721","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","created":"2023-01-27","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":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"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":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2101.09458","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","created":"2021-01-23","cited_by_count":14,"area":null},{"id":"2109.08603","title":"Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration","created":"2021-09-17","cited_by_count":14,"area":null},{"id":"2202.07415","title":"NeuPL: Neural Population Learning","created":"2022-02-15","cited_by_count":14,"area":null},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2206.08736","title":"Generalised Policy Improvement with Geometric Policy Composition","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2209.10081","title":"Revisiting Discrete Soft Actor-Critic","created":"2022-09-21","cited_by_count":13,"area":null}],"next_cursor":"100"}