{"total":162,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725,"area":"offlinerl"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239,"area":"lr"},{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108,"area":"deeprl"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"area":null},{"id":"2106.00672","title":"What Matters for Adversarial Imitation Learning?","created":"2021-06-01","cited_by_count":70,"area":"offlinerl"},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","cited_by_count":68,"area":null},{"id":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67,"area":"alignment"},{"id":"2506.10910","title":"Magistral","created":"2025-06-12","cited_by_count":60,"area":"lr"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"area":"lr"},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"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":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2305.16554","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","created":"2023-05-26","cited_by_count":33,"area":"agents"},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2203.05194","title":"Learning Torque Control for Quadrupedal Locomotion","created":"2022-03-10","cited_by_count":29,"area":null},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"area":"lr"},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2405.19153","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","created":"2024-05-29","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":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2111.07775","title":"Learning Representations for Pixel-based Control: What Matters and Why?","created":"2021-11-15","cited_by_count":24,"area":null},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2305.14502","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2304.04591","title":"For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal","created":"2023-04-10","cited_by_count":22,"area":"offlinerl"},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2412.12442","title":"Multi-Task Reinforcement Learning for Quadrotors","created":"2024-12-17","cited_by_count":20,"area":"deeprl"},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2106.03442","title":"Average-Reward Reinforcement Learning with Trust Region Methods","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2505.22974","title":"Learning coordinated badminton skills for legged manipulators","created":"2025-05-29","cited_by_count":19,"area":"deeprl"},{"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":"2105.12034","title":"Hyperparameter Selection for Imitation Learning","created":"2021-05-25","cited_by_count":17,"area":"offlinerl"},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2402.07157","title":"Natural Language Reinforcement Learning","created":"2024-02-11","cited_by_count":17,"area":"lr"},{"id":"2506.20966","title":"Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends","created":"2025-06-26","cited_by_count":17,"area":"mllm"},{"id":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2307.10142","title":"Benchmarking Potential Based Rewards for Learning Humanoid Locomotion","created":"2023-07-19","cited_by_count":15,"area":null},{"id":"2412.07165","title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","created":"2024-12-10","cited_by_count":15,"area":"deeprl"},{"id":"2403.16442","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","created":"2024-03-25","cited_by_count":14,"area":"mllm"},{"id":"2504.02587","title":"Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme","created":"2025-04-03","cited_by_count":14,"area":"lr"},{"id":"2406.02081","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2406.11978","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","created":"2024-06-17","cited_by_count":13,"area":"agents"},{"id":"2106.03955","title":"Correcting Momentum in Temporal Difference Learning","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2206.00702","title":"Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search","created":"2022-06-01","cited_by_count":12,"area":null},{"id":"2412.17113","title":"Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps","created":"2024-12-22","cited_by_count":11,"area":"deeprl"},{"id":"2210.08607","title":"The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2401.12205","title":"Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization","created":"2024-01-22","cited_by_count":10,"area":"deeprl"},{"id":"2410.01220","title":"Effective Tuning Strategies for Generalist Robot Manipulation Policies","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2108.01867","title":"A Pragmatic Look at Deep Imitation Learning","created":"2021-08-04","cited_by_count":9,"area":"offlinerl"},{"id":"2111.15382","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","created":"2021-11-30","cited_by_count":8,"area":null},{"id":"2205.11184","title":"An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2205.14557","title":"Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning","created":"2022-05-29","cited_by_count":8,"area":null},{"id":"2210.13611","title":"Understanding the Evolution of Linear Regions in Deep Reinforcement Learning","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2304.10770","title":"DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2410.22568","title":"Fast Deep Hedging with Second-Order Optimization","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2501.09080","title":"Average-Reward Soft Actor-Critic","created":"2025-01-15","cited_by_count":6,"area":"deeprl"},{"id":"2511.03527","title":"Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments","created":"2025-11-05","cited_by_count":6,"area":"lr"},{"id":"2109.10552","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2301.12802","title":"Planning Multiple Epidemic Interventions with Reinforcement Learning","created":"2023-01-30","cited_by_count":5,"area":null},{"id":"2306.10404","title":"The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions","created":"2023-06-17","cited_by_count":5,"area":null},{"id":"2309.02711","title":"Addressing imperfect symmetry: A novel symmetry-learning actor-critic extension","created":"2023-09-06","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2401.13662","title":"The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations","created":"2024-01-24","cited_by_count":5,"area":"deeprl"},{"id":"2402.04536","title":"Tactile-based Object Retrieval From Granular Media","created":"2024-02-07","cited_by_count":5,"area":null},{"id":"2411.14251","title":"Natural Language Reinforcement Learning","created":"2024-11-21","cited_by_count":5,"area":"lr"},{"id":"2203.06250","title":"Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2206.01812","title":"Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2305.06851","title":"Policy Gradient Algorithms Implicitly Optimize by Continuation","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2310.00112","title":"Reinforcement Learning for Node Selection in Branch-and-Bound","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4,"area":"offlinerl"},{"id":"2410.08893","title":"Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient","created":"2024-10-11","cited_by_count":4,"area":"wm"},{"id":"2603.20147","title":"AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning","created":"2026-03-20","cited_by_count":4,"area":"deeprl"},{"id":"2104.02372","title":"The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2112.03149","title":"Distilled Domain Randomization","created":"2021-12-06","cited_by_count":3,"area":null},{"id":"2305.13164","title":"INVICTUS: Optimizing Boolean Logic Circuit Synthesis via Synergistic Learning and Search","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2402.17402","title":"Beacon, a lightweight deep reinforcement learning benchmark library for flow control","created":"2024-02-27","cited_by_count":3,"area":"deeprl"},{"id":"2411.00666","title":"Beyond the Boundaries of Proximal Policy Optimization","created":"2024-11-01","cited_by_count":3,"area":"deeprl"},{"id":"2503.01178","title":"Differentiable Information Enhanced Model-Based Reinforcement Learning","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2506.13755","title":"MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.14142","title":"From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2101.04167","title":"First-Order Problem Solving through Neural MCTS based Reinforcement Learning","created":"2021-01-11","cited_by_count":2,"area":null},{"id":"2209.09344","title":"Understanding reinforcement learned crowds","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2306.17766","title":"Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2505.15040","title":"RLBenchNet: The Right Network for the Right Reinforcement Learning Task","created":"2025-05-21","cited_by_count":2,"area":"ssm"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2201.12819","title":"A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithms","created":"2022-01-30","cited_by_count":1,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null}],"next_cursor":"100"}