{"total":195,"rows":[{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459,"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":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"area":null},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2310.04582","title":"Universal Humanoid Motion Representations for Physics-Based Control","created":"2023-10-06","cited_by_count":116,"area":null},{"id":"2104.11203","title":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","created":"2021-04-22","cited_by_count":95,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"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":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"area":null},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2309.00987","title":"Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation","created":"2023-09-02","cited_by_count":49,"area":null},{"id":"2301.13868","title":"PADL: Language-Directed Physics-Based Character Control","created":"2023-01-31","cited_by_count":48,"area":null},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38,"area":null},{"id":"2308.07200","title":"Neural Categorical Priors for Physics-Based Character Control","created":"2023-08-14","cited_by_count":38,"area":null},{"id":"2308.15143","title":"Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models","created":"2023-08-29","cited_by_count":37,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","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":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"area":null},{"id":"2212.14020","title":"A System-Level View on Out-of-Distribution Data in Robotics","created":"2022-12-28","cited_by_count":33,"area":null},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2102.13045","title":"Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods","created":"2021-02-25","cited_by_count":31,"area":null},{"id":"2103.10860","title":"Universal Trading for Order Execution with Oracle Policy Distillation","created":"2021-01-28","cited_by_count":30,"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":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2305.08466","title":"Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives","created":"2023-05-15","cited_by_count":30,"area":null},{"id":"2211.10445","title":"Building a Subspace of Policies for Scalable Continual Learning","created":"2022-11-18","cited_by_count":28,"area":null},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2110.06972","title":"Block Contextual MDPs for Continual Learning","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2201.00042","title":"Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2105.01648","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","created":"2021-05-04","cited_by_count":24,"area":null},{"id":"2106.11072","title":"Techniques for Symbol Grounding with SATNet","created":"2021-06-16","cited_by_count":24,"area":null},{"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":"2402.09844","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","created":"2024-02-15","cited_by_count":21,"area":null},{"id":"2206.12984","title":"Improving Policy Optimization with Generalist-Specialist Learning","created":"2022-06-26","cited_by_count":20,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2106.02300","title":"AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2106.02654","title":"Churn Reduction via Distillation","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2107.05627","title":"Hierarchical Neural Dynamic Policies","created":"2021-07-12","cited_by_count":17,"area":null},{"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":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","cited_by_count":17,"area":null},{"id":"2111.04686","title":"Reinforcement Learning for Mixed Autonomy Intersections","created":"2021-11-08","cited_by_count":16,"area":null},{"id":"2112.08907","title":"Inherently Explainable Reinforcement Learning in Natural Language","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2310.00239","title":"AdaptNet: Policy Adaptation for Physics-Based Character Control","created":"2023-09-30","cited_by_count":16,"area":null},{"id":"2112.04467","title":"CoMPS: Continual Meta Policy Search","created":"2021-12-08","cited_by_count":15,"area":null},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2209.00347","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","created":"2022-09-01","cited_by_count":14,"area":null},{"id":"2210.12624","title":"Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach","created":"2022-10-23","cited_by_count":14,"area":null},{"id":"2306.17465","title":"FedBone: Towards Large-Scale Federated Multi-Task Learning","created":"2023-06-30","cited_by_count":14,"area":null},{"id":"2402.00152","title":"Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss","created":"2024-01-31","cited_by_count":14,"area":null},{"id":"2606.14777","title":"JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence","created":"2026-06-10","cited_by_count":14,"area":null},{"id":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2106.00517","title":"Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment","created":"2021-06-01","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":"2310.15940","title":"Combining Behaviors with the Successor Features Keyboard","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2404.07988","title":"QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer","created":"2024-04-11","cited_by_count":12,"area":null},{"id":"2107.04641","title":"Training Over-parameterized Models with Non-decomposable Objectives","created":"2021-07-09","cited_by_count":11,"area":null},{"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":"2201.06714","title":"AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization","created":"2022-01-18","cited_by_count":11,"area":null},{"id":"2208.05056","title":"Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2","created":"2022-08-09","cited_by_count":11,"area":null},{"id":"2210.08872","title":"PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning","created":"2022-10-17","cited_by_count":11,"area":null},{"id":"2402.06570","title":"Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control","created":"2024-02-09","cited_by_count":11,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2110.10305","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2302.02477","title":"Offline Learning of Closed-Loop Deep Brain Stimulation Controllers for Parkinson Disease Treatment","created":"2023-02-05","cited_by_count":8,"area":null},{"id":"2309.13285","title":"Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning","created":"2023-09-23","cited_by_count":8,"area":null},{"id":"2103.10000","title":"Human-Inspired Multi-Agent Navigation using Knowledge Distillation","created":"2021-03-18","cited_by_count":7,"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":"2203.08412","title":"CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2301.00141","title":"Self-Activating Neural Ensembles for Continual Reinforcement Learning","created":"2022-12-31","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":"2312.08751","title":"Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\\infty$ Lipschitz Policy Networks","created":"2023-12-14","cited_by_count":7,"area":null},{"id":"2108.12988","title":"Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning","created":"2021-08-30","cited_by_count":6,"area":null},{"id":"2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","created":"2022-11-24","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":"2307.14382","title":"When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2108.06898","title":"Neural-to-Tree Policy Distillation with Policy Improvement Criterion","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2203.03187","title":"Knowledge Amalgamation for Object Detection with Transformers","created":"2022-03-07","cited_by_count":5,"area":null},{"id":"2204.05893","title":"Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2205.14410","title":"Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning","created":"2022-05-28","cited_by_count":5,"area":null},{"id":"2207.09071","title":"Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks","created":"2022-07-19","cited_by_count":5,"area":null},{"id":"2211.13337","title":"Multi-Environment Pretraining Enables Transfer to Action Limited Datasets","created":"2022-11-23","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":"2309.07265","title":"Safe and Accelerated Deep Reinforcement Learning-based O-RAN Slicing: A Hybrid Transfer Learning Approach","created":"2023-09-13","cited_by_count":5,"area":null}],"next_cursor":"100"}