{"total":86,"rows":[{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158,"area":null},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91,"area":"offlinerl"},{"id":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83,"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":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2206.10607","title":"MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer","created":"2022-06-20","cited_by_count":34,"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":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","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":"2408.05804","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","created":"2024-08-11","cited_by_count":23,"area":null},{"id":"2510.00739","title":"TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning","created":"2025-10-01","cited_by_count":22,"area":"deeprl"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"id":"2411.19418","title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","created":"2024-11-29","cited_by_count":20,"area":"deeprl"},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16,"area":"deeprl"},{"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":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2406.16121","title":"Diffusion Spectral Representation for Reinforcement Learning","created":"2024-06-23","cited_by_count":15,"area":"diffusion"},{"id":"2406.17718","title":"When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning","created":"2024-06-25","cited_by_count":14,"area":"deeprl"},{"id":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","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":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2210.13153","title":"Reachability-Aware Laplacian Representation in Reinforcement Learning","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2410.23022","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","created":"2024-10-30","cited_by_count":10,"area":"agents"},{"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":"2411.03169","title":"Pre-trained Visual Dynamics Representations for Efficient Policy Learning","created":"2024-11-05","cited_by_count":8,"area":"deeprl"},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","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":"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":"2412.05718","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","created":"2024-12-07","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":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2311.00140","title":"Adaptive and non-adaptive minimax rates for weighted Laplacian-eigenmap based nonparametric regression","created":"2023-10-31","cited_by_count":5,"area":null},{"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":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"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":"2505.16217","title":"Reward-Aware Proto-Representations in Reinforcement Learning","created":"2025-05-22","cited_by_count":4,"area":"deeprl"},{"id":"2507.13181","title":"Spectral Bellman Method: Unifying Representation and Exploration in RL","created":"2025-07-17","cited_by_count":4,"area":"deeprl"},{"id":"2310.14509","title":"Iteratively Learn Diverse Strategies with State Distance Information","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2502.10790","title":"Which Features are Best for Successor Features?","created":"2025-02-15","cited_by_count":3,"area":"deeprl"},{"id":"2507.20853","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","created":"2025-07-28","cited_by_count":3,"area":"deeprl"},{"id":"2509.23802","title":"STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"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":"2207.02296","title":"A Tutorial on the Spectral Theory of Markov Chains","created":"2022-07-05","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":"2307.08033","title":"Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning","created":"2023-07-16","cited_by_count":2,"area":null},{"id":"2402.14985","title":"Nonsmooth Nonparametric Regression via Fractional Laplacian Eigenmaps","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2603.09400","title":"Reward Prediction with Factorized World States","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","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":"2310.10818","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2506.09276","title":"Learning The Minimum Action Distance","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2603.08558","title":"Impact of Connectivity on Laplacian Representations in Reinforcement Learning","created":"2026-03-09","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":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"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":"2312.00966","title":"Spectral Temporal Contrastive Learning","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2403.10875","title":"Probabilistic World Modeling with Asymmetric Distance Measure","created":"2024-03-16","cited_by_count":0,"area":"wm"},{"id":"2510.21952","title":"Revisiting Orbital Minimization Method for Neural Operator Decomposition","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.07734","title":"Global Optimization on Graph-Structured Data via Gaussian Processes with Spectral Representations","created":"2025-11-11","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":"2601.21391","title":"Intrinsic Reward Policy Optimization for Sparse-Reward Environments","created":"2026-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2602.00403","title":"DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning","created":"2026-01-30","cited_by_count":0,"area":"deeprl"},{"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":"2609.05104","title":"Compact Bellman-Grounded Cognitive Maps for Cost-Aware Navigation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.19414","title":"Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation","created":"2026-09-16","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35615","title":"Behavioral Foundation Models for Quality Diversity","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01373","title":"Learning Commute-Time-Preserving World Models for Planning","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.03604","title":"Mastering Atari 2600 Games with Discovered Options","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.05350","title":"Task Inference Beyond Least Squares in Behavioral Foundation Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.14400","title":"Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations","created":"2026-10-09","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}