{"total":122,"rows":[{"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":"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":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131,"area":"wm"},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101,"area":"wm"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86,"area":"synth"},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"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":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65,"area":null},{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51,"area":"diffusion"},{"id":"2412.13194","title":"Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents","created":"2024-12-17","cited_by_count":50,"area":"agents"},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38,"area":null},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","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":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31,"area":null},{"id":"2106.14305","title":"Unsupervised Skill Discovery with Bottleneck Option Learning","created":"2021-06-27","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":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","cited_by_count":24,"area":null},{"id":"2110.07940","title":"Wasserstein Unsupervised Reinforcement Learning","created":"2021-10-15","cited_by_count":22,"area":null},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22,"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":"2504.03515","title":"Dexterous Manipulation through Imitation Learning: A Survey","created":"2025-04-04","cited_by_count":21,"area":"offlinerl"},{"id":"2106.00669","title":"Discovering Diverse Nearly Optimal Policies with Successor Features","created":"2021-06-01","cited_by_count":20,"area":null},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"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":"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":"2104.05043","title":"Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning","created":"2021-04-11","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":"2112.08746","title":"Unsupervised Reinforcement Learning in Multiple Environments","created":"2021-12-16","cited_by_count":17,"area":null},{"id":"2407.08464","title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","created":"2024-07-11","cited_by_count":17,"area":"deeprl"},{"id":"2105.00371","title":"Discovering Diverse Athletic Jumping Strategies","created":"2021-05-02","cited_by_count":16,"area":null},{"id":"2103.10972","title":"Learning Task Decomposition with Ordered Memory Policy Network","created":"2021-03-19","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":"2112.15025","title":"Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates","created":"2021-12-30","cited_by_count":14,"area":null},{"id":"2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2107.07506","title":"Adaptable Agent Populations via a Generative Model of Policies","created":"2021-07-15","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":"2506.04287","title":"Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback","created":"2025-06-04","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":"2203.11176","title":"One After Another: Learning Incremental Skills for a Changing World","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"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":"2310.19424","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","created":"2023-10-30","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":"2211.14003","title":"Assistive Teaching of Motor Control Tasks to Humans","created":"2022-11-25","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":"2310.20178","title":"Learning to Discover Skills through Guidance","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"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":"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":"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":"2307.02728","title":"Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2202.11079","title":"Reward-Free Policy Space Compression for Reinforcement Learning","created":"2022-02-22","cited_by_count":6,"area":null},{"id":"2303.04592","title":"Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2410.07877","title":"Constrained Skill Discovery: Quadruped Locomotion with Unsupervised Reinforcement Learning","created":"2024-10-10","cited_by_count":6,"area":"deeprl"},{"id":"1912.12612","title":"Hierarchical Variational Imitation Learning of Control Programs","created":"2019-12-29","cited_by_count":5,"area":"offlinerl"},{"id":"2202.04675","title":"Bayesian Nonparametrics for Offline Skill Discovery","created":"2022-02-09","cited_by_count":5,"area":"offlinerl"},{"id":"2202.08266","title":"Open-Ended Reinforcement Learning with Neural Reward Functions","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2502.03752","title":"Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning","created":"2025-02-06","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":"2107.08398","title":"Unsupervised Skill-Discovery and Skill-Learning in Minecraft","created":"2021-07-18","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":"2304.05008","title":"Habits and goals in synergy: a variational Bayesian framework for behavior","created":"2023-04-11","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":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2410.15910","title":"Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning","created":"2024-10-21","cited_by_count":4,"area":"offlinerl"},{"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":"2509.22566","title":"From Parameters to Behaviors: Unsupervised Compression of the Policy Space","created":"2025-09-26","cited_by_count":4,"area":"deeprl"},{"id":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2207.05018","title":"Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning","created":"2022-07-11","cited_by_count":3,"area":null},{"id":"2404.07465","title":"Offline Reinforcement Learning with Domain-Unlabeled Data","created":"2024-04-11","cited_by_count":3,"area":"offlinerl"},{"id":"2409.15128","title":"The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2410.04855","title":"Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2501.17431","title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","created":"2025-01-29","cited_by_count":3,"area":"alignment"},{"id":"2509.10656","title":"Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2501.04426","title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2503.14973","title":"Behaviour Discovery and Attribution for Explainable Reinforcement Learning","created":"2025-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","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":"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":"2605.06145","title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","created":"2026-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2605.11387","title":"Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies","created":"2026-05-12","cited_by_count":2,"area":"deeprl"},{"id":"2202.08444","title":"A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2301.02375","title":"Centralized Cooperative Exploration Policy for Continuous Control Tasks","created":"2023-01-06","cited_by_count":1,"area":null},{"id":"2303.08909","title":"Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning","created":"2023-03-15","cited_by_count":1,"area":null},{"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":"2410.11155","title":"Latent-Predictive Empowerment: Measuring Empowerment without a Simulator","created":"2024-10-15","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":"2505.01979","title":"D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection","created":"2025-05-04","cited_by_count":1,"area":"deeprl"},{"id":"2505.15782","title":"Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2601.20765","title":"Less is More: Clustered Cross-Covariance Control for Offline RL","created":"2026-01-28","cited_by_count":1,"area":"offlinerl"}],"next_cursor":"100"}