{"total":54,"rows":[{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290,"area":null},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81,"area":"offlinerl"},{"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":"2406.17098","title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","created":"2024-06-24","cited_by_count":56,"area":"deeprl"},{"id":"2205.02300","title":"P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision","created":"2022-05-04","cited_by_count":52,"area":null},{"id":"2107.00646","title":"Learning to See before Learning to Act: Visual Pre-training for Manipulation","created":"2021-07-01","cited_by_count":51,"area":null},{"id":"2110.14096","title":"Towards Robust Bisimulation Metric Learning","created":"2021-10-27","cited_by_count":49,"area":null},{"id":"2110.13625","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","created":"2021-10-26","cited_by_count":47,"area":null},{"id":"2204.13060","title":"Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning","created":"2022-04-27","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":"2410.08328","title":"Agents Thinking Fast and Slow: A Talker-Reasoner Architecture","created":"2024-10-10","cited_by_count":36,"area":"lr"},{"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":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31,"area":null},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2204.11561","title":"Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25,"area":null},{"id":"2111.09858","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","created":"2021-11-18","cited_by_count":23,"area":null},{"id":"2105.00931","title":"GridToPix: Training Embodied Agents with Minimal Supervision","created":"2021-04-14","cited_by_count":21,"area":null},{"id":"2309.00082","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","created":"2023-08-31","cited_by_count":18,"area":null},{"id":"2105.14750","title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"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":"2210.15206","title":"Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision","created":"2022-10-27","cited_by_count":13,"area":"synth"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"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":"2306.03857","title":"Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2309.07675","title":"Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysis","created":"2023-09-14","cited_by_count":6,"area":null},{"id":"2401.09870","title":"Reconciling Spatial and Temporal Abstractions for Goal Representation","created":"2024-01-18","cited_by_count":6,"area":"deeprl"},{"id":"2004.08356","title":"Goal-conditioned Batch Reinforcement Learning for Rotation Invariant Locomotion","created":"2020-04-17","cited_by_count":4,"area":"offlinerl"},{"id":"2107.08398","title":"Unsupervised Skill-Discovery and Skill-Learning in Minecraft","created":"2021-07-18","cited_by_count":4,"area":null},{"id":"2208.08056","title":"Sampling Through the Lens of Sequential Decision Making","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2409.05358","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2108.01851","title":"Risk Conditioned Neural Motion Planning","created":"2021-08-04","cited_by_count":3,"area":null},{"id":"2310.14509","title":"Iteratively Learn Diverse Strategies with State Distance Information","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2608.30640","title":"Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL","created":"2026-08-31","cited_by_count":3,"area":"deeprl"},{"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":"2606.20363","title":"Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2106.05802","title":"Metric Policy Representations for Opponent Modeling","created":"2021-06-10","cited_by_count":1,"area":null},{"id":"2305.06297","title":"Why Don't You Do Something About It? Outlining Connections between AI Explanations and User Actions","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2307.12063","title":"Balancing Exploration and Exploitation in Hierarchical Reinforcement Learning via Latent Landmark Graphs","created":"2023-07-22","cited_by_count":1,"area":null},{"id":"2402.15579","title":"CI w/o TN: Context Injection without Task Name for Procedure Planning","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2601.22496","title":"Action-Sufficient Goal Representations","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2605.20609","title":"Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"offlinerl"},{"id":"2605.30656","title":"Learning to Perceive the World Through Control: Empowerment-Based Representation Learning","created":"2026-05-28","cited_by_count":1,"area":"deeprl"},{"id":"2306.17484","title":"Landmark Guided Active Exploration with State-specific Balance Coefficient","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2312.11027","title":"Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making","created":"2023-12-18","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":"2602.05459","title":"Beyond Success Rates: Trainability and Extractability for Offline GCRL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2608.09771","title":"SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation","created":"2026-08-10","cited_by_count":0,"area":"wm"},{"id":"2610.05338","title":"On Semi-Markov Suboptimality in Hierarchical Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}