{"total":178,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"area":"synth"},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519,"area":"vla"},{"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":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"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":"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":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124,"area":"mllm"},{"id":"2104.05859","title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","created":"2021-04-12","cited_by_count":121,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"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":"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":"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":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"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":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"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":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"area":null},{"id":"2302.11289","title":"Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning","created":"2023-02-22","cited_by_count":51,"area":null},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2203.03137","title":"MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning","created":"2022-03-07","cited_by_count":48,"area":null},{"id":"2101.08387","title":"A Survey on Ensemble Learning under the Era of Deep Learning","created":"2021-01-21","cited_by_count":47,"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":"2210.11348","title":"Hypernetworks in Meta-Reinforcement Learning","created":"2022-10-20","cited_by_count":42,"area":null},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39,"area":null},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36,"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":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","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":"2107.02629","title":"Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation","created":"2021-07-06","cited_by_count":29,"area":"distill"},{"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":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28,"area":null},{"id":"2307.03719","title":"Polybot: Training One Policy Across Robots While Embracing Variability","created":"2023-07-07","cited_by_count":28,"area":null},{"id":"2206.12279","title":"AnyMorph: Learning Transferable Polices By Inferring Agent Morphology","created":"2022-06-17","cited_by_count":27,"area":null},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"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":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20,"area":null},{"id":"2102.07097","title":"Domain Adversarial Reinforcement Learning","created":"2021-02-14","cited_by_count":19,"area":null},{"id":"2108.01005","title":"Sequoia: A Software Framework to Unify Continual Learning Research","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2202.07013","title":"Robust Policy Learning over Multiple Uncertainty Sets","created":"2022-02-14","cited_by_count":18,"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":"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":"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":"2406.09738","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","created":"2024-06-14","cited_by_count":15,"area":"offlinerl"},{"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":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2107.09046","title":"Playful Interactions for Representation Learning","created":"2021-07-19","cited_by_count":13,"area":"offlinerl"},{"id":"2210.02750","title":"Meta Reinforcement Learning for Optimal Design of Legged Robots","created":"2022-10-06","cited_by_count":13,"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":"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":"2210.11579","title":"Model-based Lifelong Reinforcement Learning with Bayesian Exploration","created":"2022-10-20","cited_by_count":12,"area":null},{"id":"2112.12490","title":"Curriculum Learning for Safe Mapless Navigation","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2305.17581","title":"Knowledge Distillation Performs Partial Variance Reduction","created":"2023-05-27","cited_by_count":11,"area":"distill"},{"id":"2311.07514","title":"VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search","created":"2023-11-13","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":"2506.05982","title":"MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks","created":"2025-06-06","cited_by_count":11,"area":null},{"id":"2101.04178","title":"Action Priors for Large Action Spaces in Robotics","created":"2021-01-11","cited_by_count":10,"area":null},{"id":"2205.03353","title":"How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation","created":"2022-05-06","cited_by_count":9,"area":"offlinerl"},{"id":"2412.11499","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","created":"2024-12-16","cited_by_count":9,"area":"agents"},{"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":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2306.01839","title":"Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2306.14403","title":"Anomaly Detection with Score Distribution Discrimination","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2108.06526","title":"Fractional Transfer Learning for Deep Model-Based Reinforcement Learning","created":"2021-08-14","cited_by_count":6,"area":"wm"},{"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":"2302.08063","title":"MINOTAUR: Multi-task Video Grounding From Multimodal Queries","created":"2023-02-16","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":"2410.02068","title":"Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2109.09889","title":"A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning","created":"2021-09-21","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":"2412.13492","title":"Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2505.19080","title":"ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning","created":"2025-05-25","cited_by_count":5,"area":"vla"},{"id":"2106.08199","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","created":"2021-06-15","cited_by_count":4,"area":"offlinerl"},{"id":"2106.08902","title":"Adaptive Clustering and Personalization in Multi-Agent Stochastic Linear Bandits","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2202.12174","title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","created":"2022-02-24","cited_by_count":4,"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":"2210.12448","title":"Probing Transfer in Deep Reinforcement Learning without Task Engineering","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2312.00292","title":"SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection","created":"2023-12-01","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":"2506.23285","title":"Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification","created":"2025-06-29","cited_by_count":4,"area":"distill"},{"id":"2601.07197","title":"Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics","created":"2026-01-12","cited_by_count":4,"area":null},{"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":"2109.08218","title":"SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning","created":"2021-09-16","cited_by_count":3,"area":null}],"next_cursor":"100"}