{"total":81,"rows":[{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"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":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"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":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28,"area":null},{"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":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27,"area":null},{"id":"2102.01514","title":"Metrics and continuity in reinforcement learning","created":"2021-02-02","cited_by_count":26,"area":null},{"id":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"area":null},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"area":null},{"id":"2107.05545","title":"Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing","created":"2021-07-12","cited_by_count":23,"area":null},{"id":"2208.08731","title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","created":"2022-08-18","cited_by_count":21,"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":"2202.03466","title":"Reward-Respecting Subtasks for Model-Based Reinforcement Learning","created":"2022-02-07","cited_by_count":16,"area":null},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2206.08736","title":"Generalised Policy Improvement with Geometric Policy Composition","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2310.10833","title":"Proper Laplacian Representation Learning","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"area":null},{"id":"2210.13153","title":"Reachability-Aware Laplacian Representation in Reinforcement Learning","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2505.23692","title":"Mobi-$\\pi$: Mobilizing Your Robot Learning Policy","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"area":null},{"id":"2307.11629","title":"Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2110.13855","title":"Average-Reward Learning and Planning with Options","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2106.03853","title":"DisTop: Discovering a Topological representation to learn diverse and rewarding skills","created":"2021-06-06","cited_by_count":7,"area":null},{"id":"2203.11369","title":"Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2306.09509","title":"Granger Causal Interaction Skill Chains","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2311.05490","title":"General Policies, Subgoal Structure, and Planning Width","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2204.13906","title":"Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery","created":"2022-04-29","cited_by_count":5,"area":null},{"id":"2306.09980","title":"Creating Multi-Level Skill Hierarchies in Reinforcement Learning","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2201.08227","title":"Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphs","created":"2022-01-20","cited_by_count":4,"area":null},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2205.15752","title":"Hierarchies of Reward Machines","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2302.02984","title":"Robust Subtask Learning for Compositional Generalization","created":"2023-02-06","cited_by_count":4,"area":null},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2204.10374","title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","created":"2022-04-21","cited_by_count":3,"area":null},{"id":"2205.12515","title":"Toward Discovering Options that Achieve Faster Planning","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2203.00669","title":"Hierarchical Reinforcement Learning with AI Planning Models","created":"2022-03-01","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":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2401.09491","title":"Memory, Space, and Planning: Multiscale Predictive Representations","created":"2024-01-16","cited_by_count":2,"area":null},{"id":"2412.06333","title":"Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2606.15386","title":"A Compositional Framework for Open-ended Intelligence","created":"2026-06-13","cited_by_count":2,"area":null},{"id":"2109.04149","title":"DROP: Deep relocating option policy for optimal ride-hailing vehicle repositioning","created":"2021-09-09","cited_by_count":1,"area":null},{"id":"2308.07843","title":"Dyadic Reinforcement Learning","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2310.01569","title":"Iterative Option Discovery for Planning, by Planning","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2403.16824","title":"On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies","created":"2024-03-25","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":"2502.03405","title":"Deep Clustering via Probabilistic Ratio-Cut Optimization","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2602.07730","title":"The Laplacian Keyboard: Beyond the Linear Span","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2606.29980","title":"Exploration and Online Transfer with Behavioral Foundation Models","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2609.02322","title":"What Is Worth Representing? Representational Empowerment for Continual Model Construction","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2609.36473","title":"Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2201.01836","title":"A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2206.04993","title":"The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2207.14589","title":"Stochastic Parallelizable Eigengap Dilation for Large Graph Clustering","created":"2022-07-29","cited_by_count":0,"area":null},{"id":"2210.03269","title":"Multi-agent Deep Covering Skill Discovery","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2212.11726","title":"Reusable Options through Gradient-based Meta Learning","created":"2022-12-22","cited_by_count":0,"area":null},{"id":"2301.00009","title":"On the Geometry of Reinforcement Learning in Continuous State and Action Spaces","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2303.07397","title":"Fast exploration and learning of latent graphs with aliased observations","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2306.04902","title":"A Cover Time Study of a non-Markovian Algorithm","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2306.17204","title":"Learning Environment Models with Continuous Stochastic Dynamics","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2312.00966","title":"Spectral Temporal Contrastive Learning","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2512.24827","title":"Inter-Agent Relative Representations for Multi-Agent Option Discovery","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.12753","title":"Hierarchical Successor Representation for Robust Transfer","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.20103","title":"Spectral Alignment in Forward-Backward Representations via Temporal Abstraction","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2608.11349","title":"Dynamics Models for Offline Hyperparameter Selection in Real-World RL","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.05508","title":"When Do Options Help? Policy Necrosis and Redundant Coverage in Option-Critic","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}