{"total":144,"rows":[{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"2106.06333","title":"Invariant Information Bottleneck for Domain Generalization","created":"2021-06-11","cited_by_count":86,"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":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71,"area":null},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62,"area":null},{"id":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49,"area":null},{"id":"2207.08229","title":"Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models","created":"2022-07-17","cited_by_count":45,"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":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"1809.06404","title":"Adversarial Imitation via Variational Inverse Reinforcement Learning","created":"2018-09-17","cited_by_count":36,"area":"offlinerl"},{"id":"2206.11403","title":"Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation","created":"2022-06-22","cited_by_count":31,"area":"wm"},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2102.04399","title":"How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation","created":"2021-02-08","cited_by_count":27,"area":null},{"id":"2204.08585","title":"INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2102.13100","title":"Task-Agnostic Morphology Evolution","created":"2021-02-25","cited_by_count":24,"area":null},{"id":"2201.12436","title":"Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination","created":"2022-01-28","cited_by_count":23,"area":null},{"id":"2310.00697","title":"Learning How to Propagate Messages in Graph Neural Networks","created":"2023-10-01","cited_by_count":23,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2209.07899","title":"Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions","created":"2022-09-16","cited_by_count":21,"area":"offlinerl"},{"id":"2412.08021","title":"Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning","created":"2024-12-11","cited_by_count":21,"area":"deeprl"},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2110.14457","title":"Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching","created":"2021-10-27","cited_by_count":19,"area":null},{"id":"2307.01158","title":"Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning","created":"2023-07-03","cited_by_count":19,"area":null},{"id":"2103.08107","title":"Mutual Information State Intrinsic Control","created":"2021-03-15","cited_by_count":18,"area":null},{"id":"2105.14750","title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2108.06038","title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","created":"2021-08-13","cited_by_count":17,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"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":"2106.01404","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning","created":"2021-06-02","cited_by_count":15,"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":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"area":null},{"id":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2106.04316","title":"Exploration and preference satisfaction trade-off in reward-free learning","created":"2021-06-08","cited_by_count":12,"area":"alignment"},{"id":"2107.07046","title":"Backprop-Free Reinforcement Learning with Active Neural Generative Coding","created":"2021-07-10","cited_by_count":12,"area":null},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"id":"2402.07411","title":"Potential-Based Reward Shaping For Intrinsic Motivation","created":"2024-02-12","cited_by_count":12,"area":"deeprl"},{"id":"2505.10361","title":"Plasticity as the Mirror of Empowerment","created":"2025-05-15","cited_by_count":12,"area":null},{"id":"2603.00656","title":"InfoPO: Information-Driven Policy Optimization for User-Centric Agents","created":"2026-02-28","cited_by_count":12,"area":"agents"},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2112.03899","title":"Information is Power: Intrinsic Control via Information Capture","created":"2021-12-07","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2207.05631","title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization","created":"2022-07-12","cited_by_count":10,"area":null},{"id":"2212.06988","title":"Efficient Exploration in Resource-Restricted Reinforcement Learning","created":"2022-12-14","cited_by_count":10,"area":null},{"id":"2312.09539","title":"Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learning","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2210.06702","title":"A Mixture of Surprises for Unsupervised Reinforcement Learning","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2303.06710","title":"Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning","created":"2023-03-12","cited_by_count":9,"area":null},{"id":"2503.01584","title":"SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models","created":"2025-03-03","cited_by_count":9,"area":"wm"},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2205.12381","title":"First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization","created":"2022-05-24","cited_by_count":8,"area":null},{"id":"2301.00005","title":"Intrinsic Motivation in Dynamical Control Systems","created":"2022-12-29","cited_by_count":8,"area":null},{"id":"2310.08702","title":"ELDEN: Exploration via Local Dependencies","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7,"area":null},{"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":"2307.02728","title":"Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2403.16369","title":"Learning Action-based Representations Using Invariance","created":"2024-03-25","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":"2209.09174","title":"Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2302.12617","title":"Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains","created":"2023-02-24","cited_by_count":6,"area":null},{"id":"2410.10834","title":"Focus On What Matters: Separated Models For Visual-Based RL Generalization","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"id":"2202.08266","title":"Open-Ended Reinforcement Learning with Neural Reward Functions","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2303.00451","title":"A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning","created":"2023-03-01","cited_by_count":5,"area":null},{"id":"2307.00668","title":"Active Sensing with Predictive Coding and Uncertainty Minimization","created":"2023-07-02","cited_by_count":5,"area":null},{"id":"2312.01473","title":"Regularity as Intrinsic Reward for Free Play","created":"2023-12-03","cited_by_count":5,"area":null},{"id":"2403.01112","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","created":"2024-03-02","cited_by_count":5,"area":null},{"id":"2410.09972","title":"Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions","created":"2024-10-13","cited_by_count":5,"area":"deeprl"},{"id":"2502.10077","title":"Towards Empowerment Gain through Causal Structure Learning in Model-Based RL","created":"2025-02-14","cited_by_count":5,"area":"deeprl"},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2107.08398","title":"Unsupervised Skill-Discovery and Skill-Learning in Minecraft","created":"2021-07-18","cited_by_count":4,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2409.05358","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2507.14748","title":"Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning","created":"2025-07-19","cited_by_count":4,"area":"deeprl"},{"id":"2110.14615","title":"Play to Grade: Testing Coding Games as Classifying Markov Decision Process","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2201.11685","title":"Generative Adversarial Exploration for Reinforcement Learning","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2205.11357","title":"POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2303.03787","title":"Sample-efficient Real-time Planning with Curiosity Cross-Entropy Method and Contrastive Learning","created":"2023-03-07","cited_by_count":3,"area":null},{"id":"2309.04459","title":"Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2410.12197","title":"Potential-Based Intrinsic Motivation: Preserving Optimality With Complex, Non-Markovian Shaping Rewards","created":"2024-10-16","cited_by_count":3,"area":"deeprl"},{"id":"2501.17842","title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","created":"2025-01-29","cited_by_count":3,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2509.22504","title":"Estimating the Empowerment of Language Model Agents","created":"2025-09-26","cited_by_count":3,"area":"agents"},{"id":"2510.13709","title":"Training LLM Agents to Empower Humans","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2510.17697","title":"A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2606.19998","title":"Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory","created":"2026-06-18","cited_by_count":3,"area":"vla"},{"id":"2106.00266","title":"Did I do that? Blame as a means to identify controlled effects in reinforcement learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2202.01691","title":"Solving Dynamic Principal-Agent Problems with a Rationally Inattentive Principal","created":"2022-01-18","cited_by_count":2,"area":null},{"id":"2206.01192","title":"Uniqueness and Complexity of Inverse MDP Models","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2302.04693","title":"Scaling Goal-based Exploration via Pruning Proto-goals","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2401.09034","title":"UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems","created":"2024-01-17","cited_by_count":2,"area":"deeprl"},{"id":"2411.14991","title":"Free Energy Projective Simulation (FEPS): Active inference with interpretability","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2502.15820","title":"Universal AI maximizes Variational Empowerment","created":"2025-02-20","cited_by_count":2,"area":"deeprl"},{"id":"2506.09202","title":"Policy-Based Trajectory Clustering in Offline Reinforcement Learning","created":"2025-06-10","cited_by_count":2,"area":"offlinerl"},{"id":"2510.05996","title":"Information-Theoretic Policy Pre-Training with Empowerment","created":"2025-10-07","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}