{"total":112,"rows":[{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"area":null},{"id":"2201.13425","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","created":"2022-01-31","cited_by_count":96,"area":"offlinerl"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83,"area":null},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75,"area":"offlinerl"},{"id":"2202.00161","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","created":"2022-02-01","cited_by_count":68,"area":null},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62,"area":null},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60,"area":null},{"id":"2110.05740","title":"Temporal Abstraction in Reinforcement Learning with the Successor Representation","created":"2021-10-12","cited_by_count":54,"area":null},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45,"area":"offlinerl"},{"id":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"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":"2305.16554","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","created":"2023-05-26","cited_by_count":33,"area":"agents"},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","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":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2305.04477","title":"Behavior Contrastive Learning for Unsupervised Skill Discovery","created":"2023-05-08","cited_by_count":26,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","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":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","cited_by_count":21,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"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":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","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":"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":"2310.03419","title":"Pre-Training and Fine-Tuning Generative Flow Networks","created":"2023-10-05","cited_by_count":17,"area":null},{"id":"2406.06615","title":"Language Guided Skill Discovery","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2301.11741","title":"Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation","created":"2023-01-27","cited_by_count":15,"area":null},{"id":"2109.13863","title":"A First-Occupancy Representation for Reinforcement Learning","created":"2021-09-28","cited_by_count":14,"area":null},{"id":"2312.08958","title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2403.06966","title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","created":"2024-03-11","cited_by_count":14,"area":"moe"},{"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":"2205.15623","title":"k-Means Maximum Entropy Exploration","created":"2022-05-31","cited_by_count":11,"area":null},{"id":"2210.06702","title":"A Mixture of Surprises for Unsupervised Reinforcement Learning","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","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":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9,"area":"deeprl"},{"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":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"id":"2406.00324","title":"Do's and Don'ts: Learning Desirable Skills with Instruction Videos","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2507.05477","title":"Epistemically-guided forward-backward exploration","created":"2025-07-07","cited_by_count":8,"area":"deeprl"},{"id":"2210.10913","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2212.00211","title":"A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process","created":"2022-12-01","cited_by_count":7,"area":null},{"id":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2205.01906","title":"ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2210.09566","title":"Simple Emergent Action Representations from Multi-Task Policy Training","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","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":"2410.07877","title":"Constrained Skill Discovery: Quadruped Locomotion with Unsupervised Reinforcement Learning","created":"2024-10-10","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":"2208.14928","title":"Cell-Free Latent Go-Explore","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2310.11138","title":"Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2406.16255","title":"Uncertainty-Aware Reward-Free Exploration with General Function Approximation","created":"2024-06-24","cited_by_count":5,"area":"deeprl"},{"id":"2410.05673","title":"Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem","created":"2024-10-08","cited_by_count":5,"area":"deeprl"},{"id":"2506.10629","title":"Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning","created":"2025-06-12","cited_by_count":5,"area":"deeprl"},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2205.10484","title":"Nuclear Norm Maximization Based Curiosity-Driven Learning","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2210.07426","title":"Skill-Based Reinforcement Learning with Intrinsic Reward Matching","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2211.10515","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2310.19261","title":"Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2402.06590","title":"Predictive representations: building blocks of intelligence","created":"2024-02-09","cited_by_count":4,"area":null},{"id":"2408.12130","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","created":"2024-08-22","cited_by_count":4,"area":"deeprl"},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4,"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":"2405.11740","title":"Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2409.02714","title":"MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning","created":"2024-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2502.10790","title":"Which Features are Best for Successor Features?","created":"2025-02-15","cited_by_count":3,"area":"deeprl"},{"id":"2604.17551","title":"SVL: Goal-Conditioned Reinforcement Learning as Survival Learning","created":"2026-04-19","cited_by_count":3,"area":"deeprl"},{"id":"2211.15451","title":"Discovering Unsupervised Behaviours from Full-State Trajectories","created":"2022-11-22","cited_by_count":2,"area":null},{"id":"2410.00704","title":"Contrastive Abstraction for Reinforcement Learning","created":"2024-10-01","cited_by_count":2,"area":"deeprl"},{"id":"2510.05996","title":"Information-Theoretic Policy Pre-Training with Empowerment","created":"2025-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2510.06203","title":"Reference Grounded Skill Discovery","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2605.11387","title":"Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies","created":"2026-05-12","cited_by_count":2,"area":"deeprl"},{"id":"2211.15205","title":"CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2405.02569","title":"Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features","created":"2024-05-04","cited_by_count":1,"area":null},{"id":"2406.03845","title":"Open Problem: Active Representation Learning","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2502.19544","title":"Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data","created":"2025-02-26","cited_by_count":1,"area":"wm"},{"id":"2506.04302","title":"RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming","created":"2025-06-04","cited_by_count":1,"area":"safety"},{"id":"2506.05980","title":"AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2512.10042","title":"SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation","created":"2025-12-10","cited_by_count":1,"area":"deeprl"},{"id":"2602.01619","title":"SUSD: Structured Unsupervised Skill Discovery through State Factorization","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.25464","title":"Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning","created":"2026-03-26","cited_by_count":1,"area":"deeprl"},{"id":"2604.05931","title":"Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning","created":"2026-04-07","cited_by_count":1,"area":"deeprl"},{"id":"2606.00950","title":"COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2208.11349","title":"Dynamic Memory-based Curiosity: A Bootstrap Approach for Exploration","created":"2022-08-24","cited_by_count":0,"area":null},{"id":"2208.11361","title":"Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning","created":"2022-08-24","cited_by_count":0,"area":null},{"id":"2211.03521","title":"On the importance of data collection for training general goal-reaching policies","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2305.14377","title":"Unsupervised Discovery of Continuous Skills on a Sphere","created":"2023-05-21","cited_by_count":0,"area":null}],"next_cursor":"100"}