{"total":141,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2106.07178","title":"A Comprehensive Survey on Graph Anomaly Detection with Deep Learning","created":"2021-06-14","cited_by_count":230,"area":null},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229,"area":null},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182,"area":null},{"id":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168,"area":null},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78,"area":"offlinerl"},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67,"area":null},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2111.03062","title":"Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning","created":"2021-11-04","cited_by_count":50,"area":null},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2107.02729","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","created":"2021-07-06","cited_by_count":48,"area":null},{"id":"2210.11653","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","created":"2022-10-21","cited_by_count":46,"area":null},{"id":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45,"area":null},{"id":"2401.09561","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","created":"2024-01-17","cited_by_count":44,"area":"deeprl"},{"id":"2505.11289","title":"Meta-World+: An Improved, Standardized, RL Benchmark","created":"2025-05-16","cited_by_count":43,"area":"deeprl"},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2506.00711","title":"QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training","created":"2025-05-31","cited_by_count":38,"area":"lr"},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"area":null},{"id":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35,"area":null},{"id":"2109.04778","title":"Improving Multilingual Translation by Representation and Gradient Regularization","created":"2021-09-10","cited_by_count":31,"area":null},{"id":"2106.08053","title":"On the Power of Multitask Representation Learning in Linear MDP","created":"2021-06-15","cited_by_count":30,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2105.05347","title":"Return-based Scaling: Yet Another Normalisation Trick for Deep RL","created":"2021-05-11","cited_by_count":23,"area":null},{"id":"2212.00186","title":"Multi-Task Imitation Learning for Linear Dynamical Systems","created":"2022-12-01","cited_by_count":23,"area":"offlinerl"},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2102.08370","title":"Quantifying the effects of environment and population diversity in multi-agent reinforcement learning","created":"2021-02-16","cited_by_count":22,"area":null},{"id":"2110.05734","title":"Learning Efficient Multi-Agent Cooperative Visual Exploration","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2305.19044","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","created":"2023-05-30","cited_by_count":19,"area":null},{"id":"2103.09815","title":"TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2110.04507","title":"TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations","created":"2021-10-09","cited_by_count":18,"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":"2108.11346","title":"Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral","created":"2021-08-25","cited_by_count":17,"area":null},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17,"area":"offlinerl"},{"id":"2210.04476","title":"Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks","created":"2022-10-10","cited_by_count":17,"area":null},{"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":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2306.10474","title":"A Universal Semantic-Geometric Representation for Robotic Manipulation","created":"2023-06-18","cited_by_count":16,"area":null},{"id":"2205.10787","title":"A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning","created":"2022-05-22","cited_by_count":15,"area":null},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","cited_by_count":13,"area":null},{"id":"2308.04428","title":"Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data","created":"2023-08-08","cited_by_count":13,"area":null},{"id":"2106.11779","title":"Emphatic Algorithms for Deep Reinforcement Learning","created":"2021-06-21","cited_by_count":12,"area":null},{"id":"2205.15701","title":"Provable General Function Class Representation Learning in Multitask Bandits and MDPs","created":"2022-05-31","cited_by_count":12,"area":null},{"id":"2206.00702","title":"Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search","created":"2022-06-01","cited_by_count":12,"area":null},{"id":"2203.07413","title":"Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning","created":"2022-03-14","cited_by_count":11,"area":null},{"id":"2305.17250","title":"Self-Supervised Reinforcement Learning that Transfers using Random Features","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2305.18444","title":"Continual Task Allocation in Meta-Policy Network via Sparse Prompting","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2110.05838","title":"Balancing Average and Worst-case Accuracy in Multitask Learning","created":"2021-10-12","cited_by_count":10,"area":null},{"id":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10,"area":"deeprl"},{"id":"2311.07127","title":"Multi-agent Attacks for Black-box Social Recommendations","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2206.08403","title":"Learning to Teach Fairness-aware Deep Multi-task Learning","created":"2022-06-16","cited_by_count":8,"area":null},{"id":"2309.17227","title":"MORPH: Design Co-optimization with Reinforcement Learning via a Differentiable Hardware Model Proxy","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2312.14472","title":"Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2111.07334","title":"Relative Distributed Formation and Obstacle Avoidance with Multi-agent Reinforcement Learning","created":"2021-11-14","cited_by_count":7,"area":null},{"id":"2205.08464","title":"Robust Losses for Learning Value Functions","created":"2022-05-17","cited_by_count":7,"area":null},{"id":"2311.11557","title":"Replay-enhanced Continual Reinforcement Learning","created":"2023-11-20","cited_by_count":7,"area":null},{"id":"2210.09566","title":"Simple Emergent Action Representations from Multi-Task Policy Training","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2302.00671","title":"QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing","created":"2023-02-01","cited_by_count":6,"area":null},{"id":"2107.05405","title":"Learning Expected Emphatic Traces for Deep RL","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2207.06412","title":"RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2212.04123","title":"Enhanced method for reinforcement learning based dynamic obstacle avoidance by assessment of collision risk","created":"2022-12-08","cited_by_count":5,"area":null},{"id":"2309.04974","title":"Continual Robot Learning using Self-Supervised Task Inference","created":"2023-09-10","cited_by_count":5,"area":null},{"id":"2509.14816","title":"Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution","created":"2025-09-18","cited_by_count":5,"area":"deeprl"},{"id":"2110.11404","title":"Statistical discrimination in learning agents","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2210.05355","title":"Multi-User Reinforcement Learning with Low Rank Rewards","created":"2022-10-11","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":"2407.13466","title":"LIMT: Language-Informed Multi-Task Visual World Models","created":"2024-07-18","cited_by_count":4,"area":"wm"},{"id":"2407.16807","title":"In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning","created":"2024-07-23","cited_by_count":4,"area":"deeprl"},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2410.18636","title":"Multi-agent cooperation through learning-aware policy gradients","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2502.19308","title":"WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies","created":"2025-02-26","cited_by_count":4,"area":"deeprl"},{"id":"2503.01885","title":"Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2504.04395","title":"Human-Level Competitive Pok\\'emon via Scalable Offline Reinforcement Learning with Transformers","created":"2025-04-06","cited_by_count":4,"area":"offlinerl"},{"id":"2102.09361","title":"Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning","created":"2021-02-18","cited_by_count":3,"area":null},{"id":"2204.00888","title":"Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks","created":"2022-04-02","cited_by_count":3,"area":null},{"id":"2305.17305","title":"DynaShare: Task and Instance Conditioned Parameter Sharing for Multi-Task Learning","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2306.12926","title":"Decentralized Multi-Agent Reinforcement Learning with Global State Prediction","created":"2023-06-22","cited_by_count":3,"area":null},{"id":"2308.00759","title":"Decomposition Ascribed Synergistic Learning for Unified Image Restoration","created":"2023-08-01","cited_by_count":3,"area":null},{"id":"2508.09193","title":"Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2601.04963","title":"Text as a Universal Interface for Transferable Personalization","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2603.10846","title":"Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2201.05560","title":"Demystifying Reinforcement Learning in Time-Varying Systems","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2206.00270","title":"Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2210.14361","title":"Auxiliary task discovery through generate-and-test","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2211.07447","title":"Neural Regression For Scale-Varying Targets","created":"2022-11-14","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":"2305.00768","title":"Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2403.01636","title":"Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks","created":"2024-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2406.14054","title":"Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing","created":"2024-06-20","cited_by_count":2,"area":"offlinerl"}],"next_cursor":"100"}