{"total":108,"rows":[{"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":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327,"area":null},{"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":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"area":null},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"area":"offlinerl"},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2202.00161","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","created":"2022-02-01","cited_by_count":68,"area":null},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51,"area":"diffusion"},{"id":"2110.13625","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","created":"2021-10-26","cited_by_count":47,"area":null},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2202.03060","title":"The Importance of Non-Markovianity in Maximum State Entropy Exploration","created":"2022-02-07","cited_by_count":35,"area":null},{"id":"2304.09853","title":"Bridging RL Theory and Practice with the Effective Horizon","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2104.07495","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2305.19476","title":"Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2110.10735","title":"Dynamic Bottleneck for Robust Self-Supervised Exploration","created":"2021-10-20","cited_by_count":21,"area":null},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2203.04297","title":"R\\'enyi State Entropy for Exploration Acceleration in Reinforcement Learning","created":"2022-03-08","cited_by_count":18,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2112.08746","title":"Unsupervised Reinforcement Learning in Multiple Environments","created":"2021-12-16","cited_by_count":17,"area":null},{"id":"2307.02427","title":"FOCUS: Object-Centric World Models for Robotics Manipulation","created":"2023-07-05","cited_by_count":17,"area":"wm"},{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"area":"deeprl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2109.00525","title":"Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation","created":"2021-09-01","cited_by_count":15,"area":"distill"},{"id":"2209.00347","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","created":"2022-09-01","cited_by_count":14,"area":null},{"id":"2310.07220","title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","created":"2023-10-11","cited_by_count":14,"area":null},{"id":"2506.15385","title":"Provable Maximum Entropy Manifold Exploration via Diffusion Models","created":"2025-06-18","cited_by_count":14,"area":"diffusion"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2301.10886","title":"Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning","created":"2023-01-26","cited_by_count":12,"area":null},{"id":"2205.15623","title":"k-Means Maximum Entropy Exploration","created":"2022-05-31","cited_by_count":11,"area":null},{"id":"2306.13412","title":"CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning","created":"2023-06-23","cited_by_count":11,"area":"offlinerl"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2405.19548","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","created":"2024-05-29","cited_by_count":10,"area":"deeprl"},{"id":"2305.01521","title":"Unlocking the Power of Representations in Long-term Novelty-based Exploration","created":"2023-05-02","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":"2310.19424","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2410.02511","title":"Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration","created":"2024-10-03","cited_by_count":9,"area":"agents"},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2210.00498","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2310.20178","title":"Learning to Discover Skills through Guidance","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2410.21795","title":"Robot Policy Learning with Temporal Optimal Transport Reward","created":"2024-10-29","cited_by_count":8,"area":"deeprl"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2205.10316","title":"Complex behavior from intrinsic motivation to occupy action-state path space","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2209.08842","title":"Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning","created":"2022-09-19","cited_by_count":7,"area":null},{"id":"2307.14316","title":"Reinforcement Learning by Guided Safe Exploration","created":"2023-07-26","cited_by_count":7,"area":null},{"id":"2310.18144","title":"Improving Intrinsic Exploration by Creating Stationary Objectives","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2505.09777","title":"A Survey on Large Language Models in Multimodal Recommender Systems","created":"2025-05-14","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":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2406.02295","title":"How to Explore with Belief: State Entropy Maximization in POMDPs","created":"2024-06-04","cited_by_count":6,"area":"deeprl"},{"id":"2406.12795","title":"The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2407.09247","title":"Constrained Intrinsic Motivation for Reinforcement Learning","created":"2024-07-12","cited_by_count":6,"area":"deeprl"},{"id":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2205.00943","title":"CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2207.03081","title":"DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning","created":"2022-07-07","cited_by_count":4,"area":null},{"id":"2410.06621","title":"Effective Exploration Based on the Structural Information Principles","created":"2024-10-09","cited_by_count":4,"area":"deeprl"},{"id":"2411.06965","title":"Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration","created":"2024-11-11","cited_by_count":4,"area":"offlinerl"},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2505.01336","title":"Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story","created":"2025-05-02","cited_by_count":4,"area":"deeprl"},{"id":"2301.12776","title":"PAC-Bayesian Soft Actor-Critic Learning","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2308.13661","title":"Go Beyond Imagination: Maximizing Episodic Reachability with World Models","created":"2023-08-25","cited_by_count":3,"area":"wm"},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2409.19617","title":"LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World","created":"2024-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2412.06655","title":"Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures","created":"2024-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2107.08888","title":"Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning","created":"2021-07-19","cited_by_count":2,"area":null},{"id":"2109.13588","title":"Making Curiosity Explicit in Vision-based RL","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2110.00784","title":"Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning","created":"2021-10-02","cited_by_count":2,"area":null},{"id":"2111.04345","title":"Off-policy Imitation Learning from Visual Inputs","created":"2021-11-08","cited_by_count":2,"area":"offlinerl"},{"id":"2203.02298","title":"Intrinsically-Motivated Reinforcement Learning: A Brief Introduction","created":"2022-03-03","cited_by_count":2,"area":null},{"id":"2302.11563","title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2412.03800","title":"ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2505.07815","title":"Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models","created":"2025-05-12","cited_by_count":2,"area":"mllm"},{"id":"2108.10533","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2211.15205","title":"CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2211.15233","title":"Tackling Visual Control via Multi-View Exploration Maximization","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2404.10991","title":"Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves","created":"2024-04-17","cited_by_count":1,"area":"deeprl"},{"id":"2407.05511","title":"Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization","created":"2024-07-07","cited_by_count":1,"area":null},{"id":"2407.13567","title":"Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd Navigation","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2501.12668","title":"NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2506.14648","title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","created":"2025-06-17","cited_by_count":1,"area":"alignment"},{"id":"2506.20307","title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","created":"2025-06-25","cited_by_count":1,"area":"offlinerl"},{"id":"2506.21158","title":"Diverse Mini-Batch Selection in Reinforcement Learning for Efficient Chemical Exploration in de novo Drug Design","created":"2025-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2601.11953","title":"Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration","created":"2026-01-17","cited_by_count":1,"area":"deeprl"},{"id":"2602.03201","title":"SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning","created":"2026-02-03","cited_by_count":1,"area":"deeprl"},{"id":"2303.01563","title":"Data-efficient, Explainable and Safe Box Manipulation: Illustrating the Advantages of Physical Priors in Model-Predictive Control","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2310.19805","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","created":"2023-10-07","cited_by_count":0,"area":"offlinerl"},{"id":"2312.12191","title":"CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning","created":"2023-12-19","cited_by_count":0,"area":"offlinerl"},{"id":"2407.00264","title":"External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling","created":"2024-06-28","cited_by_count":0,"area":"deeprl"},{"id":"2501.18086","title":"DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems","created":"2025-01-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}