{"total":61,"rows":[{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457,"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":"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":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"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":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31,"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":"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":"2301.02099","title":"Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping","created":"2023-01-05","cited_by_count":25,"area":null},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23,"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":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","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":"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":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"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":"2305.19370","title":"Blockwise Parallel Transformer for Large Context Models","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2205.15623","title":"k-Means Maximum Entropy Exploration","created":"2022-05-31","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":"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":"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":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","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":"2210.10913","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2310.18144","title":"Improving Intrinsic Exploration by Creating Stationary Objectives","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2205.13359","title":"Feature Forgetting in Continual Representation Learning","created":"2022-05-26","cited_by_count":6,"area":null},{"id":"2302.04009","title":"Investigating the role of model-based learning in exploration and transfer","created":"2023-02-08","cited_by_count":5,"area":null},{"id":"2205.02953","title":"Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing","created":"2022-05-05","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":"2210.07426","title":"Skill-Based Reinforcement Learning with Intrinsic Reward Matching","created":"2022-10-14","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":"2412.10778","title":"Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos","created":"2024-12-14","cited_by_count":4,"area":null},{"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":"2208.02680","title":"Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations","created":"2022-08-04","cited_by_count":3,"area":null},{"id":"2311.16996","title":"Goal-conditioned Offline Planning from Curious Exploration","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2305.17565","title":"Self-Supervised Learning of Action Affordances as Interaction Modes","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2310.08899","title":"Exploration with Principles for Diverse AI Supervision","created":"2023-10-13","cited_by_count":2,"area":null},{"id":"2602.01962","title":"Zero-Shot Off-Policy Learning","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2203.12114","title":"An Optical Control Environment for Benchmarking Reinforcement Learning Algorithms","created":"2022-03-23","cited_by_count":1,"area":null},{"id":"2211.15205","title":"CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control","created":"2022-11-28","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":"2411.13072","title":"AMaze: An intuitive benchmark generator for fast prototyping of generalizable agents","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2201.05830","title":"Physical Derivatives: Computing policy gradients by physical forward-propagation","created":"2022-01-15","cited_by_count":0,"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":"2309.17203","title":"ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2311.09692","title":"Augmenting Unsupervised Reinforcement Learning with Self-Reference","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2604.21155","title":"Multi-Agent Empowerment and Emergence of Complex Behavior in Groups","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2609.35615","title":"Behavioral Foundation Models for Quality Diversity","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}