{"total":174,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"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":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170,"area":"wm"},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"area":null},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104,"area":"offlinerl"},{"id":"2505.22660","title":"Maximizing Confidence Alone Improves Reasoning","created":"2025-05-28","cited_by_count":100,"area":"lr"},{"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":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"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":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60,"area":null},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50,"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":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43,"area":null},{"id":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"area":null},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"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":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","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":"2307.10224","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","created":"2023-07-15","cited_by_count":28,"area":null},{"id":"2201.11861","title":"The Challenges of Exploration for Offline Reinforcement Learning","created":"2022-01-27","cited_by_count":26,"area":"offlinerl"},{"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":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2509.20021","title":"Embodied AI: From LLMs to World Models","created":"2025-09-24","cited_by_count":24,"area":"wm"},{"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":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2406.10023","title":"Deep Bayesian Active Learning for Preference Modeling in Large Language Models","created":"2024-06-14","cited_by_count":19,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"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":"2307.02427","title":"FOCUS: Object-Centric World Models for Robotics Manipulation","created":"2023-07-05","cited_by_count":17,"area":"wm"},{"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":"2301.11520","title":"SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning","created":"2023-01-27","cited_by_count":16,"area":null},{"id":"2406.06615","title":"Language Guided Skill Discovery","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"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":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2407.09905","title":"Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods","created":"2024-07-13","cited_by_count":15,"area":"deeprl"},{"id":"2312.08958","title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2506.15385","title":"Provable Maximum Entropy Manifold Exploration via Diffusion Models","created":"2025-06-18","cited_by_count":14,"area":"diffusion"},{"id":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"area":null},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2403.09930","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","created":"2024-03-15","cited_by_count":13,"area":"deeprl"},{"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":"2506.00895","title":"State-Covering Trajectory Stitching for Diffusion Planners","created":"2025-06-01","cited_by_count":13,"area":"diffusion"},{"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":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"area":"offlinerl"},{"id":"2205.15623","title":"k-Means Maximum Entropy Exploration","created":"2022-05-31","cited_by_count":11,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2306.13412","title":"CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning","created":"2023-06-23","cited_by_count":11,"area":"offlinerl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2310.17139","title":"Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning","created":"2023-10-26","cited_by_count":10,"area":"offlinerl"},{"id":"2210.06702","title":"A Mixture of Surprises for Unsupervised Reinforcement Learning","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2302.05614","title":"Cross-domain Random Pre-training with Prototypes for Reinforcement Learning","created":"2023-02-11","cited_by_count":9,"area":null},{"id":"2305.01521","title":"Unlocking the Power of Representations in Long-term Novelty-based Exploration","created":"2023-05-02","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":"2410.18416","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","created":"2024-10-24","cited_by_count":9,"area":null},{"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":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","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":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.23631","title":"Intrinsically-Motivated Humans and Agents in Open-World Exploration","created":"2025-03-31","cited_by_count":8,"area":"deeprl"},{"id":"2602.16796","title":"Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning","created":"2026-02-18","cited_by_count":8,"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":"2210.10913","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"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":"2206.06719","title":"Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning","created":"2022-06-14","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":"2307.10936","title":"PASTA: Pretrained Action-State Transformer Agents","created":"2023-07-20","cited_by_count":6,"area":"agents"},{"id":"2406.02295","title":"How to Explore with Belief: State Entropy Maximization in POMDPs","created":"2024-06-04","cited_by_count":6,"area":"deeprl"},{"id":"2406.02370","title":"Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning","created":"2024-06-04","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":"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":"2406.16255","title":"Uncertainty-Aware Reward-Free Exploration with General Function Approximation","created":"2024-06-24","cited_by_count":5,"area":"deeprl"},{"id":"2409.09702","title":"GFlowNet Pretraining with Inexpensive Rewards","created":"2024-09-15","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":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2205.10484","title":"Nuclear Norm Maximization Based Curiosity-Driven Learning","created":"2022-05-21","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}],"next_cursor":"100"}