{"total":93,"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":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215,"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":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99,"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":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78,"area":null},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"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":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49,"area":null},{"id":"2210.11653","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","created":"2022-10-21","cited_by_count":46,"area":null},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"area":null},{"id":"2305.18409","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","created":"2023-05-28","cited_by_count":34,"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":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2111.04613","title":"Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems","created":"2021-11-08","cited_by_count":26,"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":"2302.11070","title":"Universal Morphology Control via Contextual Modulation","created":"2023-02-22","cited_by_count":23,"area":null},{"id":"2403.04115","title":"DNAct: Diffusion Guided Multi-Task 3D Policy Learning","created":"2024-03-07","cited_by_count":23,"area":null},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"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":"2109.01097","title":"The Functional Correspondence Problem","created":"2021-09-02","cited_by_count":20,"area":null},{"id":"2206.03271","title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning","created":"2022-06-07","cited_by_count":19,"area":null},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","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":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","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":"2407.10973","title":"Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","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":"2205.14495","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","created":"2022-05-28","cited_by_count":11,"area":null},{"id":"2208.14307","title":"Beyond Supervised Continual Learning: a Review","created":"2022-08-30","cited_by_count":11,"area":null},{"id":"2311.01075","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2307.15429","title":"Improvable Gap Balancing for Multi-Task Learning","created":"2023-07-28","cited_by_count":9,"area":null},{"id":"2112.09456","title":"Compositional Learning-based Planning for Vision POMDPs","created":"2021-12-17","cited_by_count":8,"area":null},{"id":"2211.03352","title":"Curriculum-based Asymmetric Multi-task Reinforcement Learning","created":"2022-11-07","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":"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":"2106.02626","title":"Dynamics of specialization in neural modules under resource constraints","created":"2021-06-04","cited_by_count":6,"area":null},{"id":"2210.08153","title":"CUP: Critic-Guided Policy Reuse","created":"2022-10-15","cited_by_count":6,"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":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2204.13906","title":"Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery","created":"2022-04-29","cited_by_count":5,"area":null},{"id":"2210.08217","title":"PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale","created":"2022-10-15","cited_by_count":5,"area":null},{"id":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2506.06130","title":"Gradient Similarity Surgery in Multi-Task Deep Learning","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2108.10511","title":"CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation","created":"2021-08-24","cited_by_count":4,"area":null},{"id":"2305.05898","title":"Mixture of personality improved Spiking actor network for efficient multi-agent cooperation","created":"2023-05-10","cited_by_count":4,"area":null},{"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":"2110.01833","title":"Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2110.03032","title":"Learning Multi-Objective Curricula for Robotic Policy Learning","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2110.10255","title":"A Simple Approach to Continual Learning by Transferring Skill Parameters","created":"2021-10-19","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":"2308.13957","title":"Differentiable Weight Masks for Domain Transfer","created":"2023-08-26","cited_by_count":2,"area":null},{"id":"2502.13935","title":"Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and Comprehensibility","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2507.06628","title":"Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2112.07222","title":"Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module","created":"2021-12-14","cited_by_count":1,"area":null},{"id":"2209.10072","title":"On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2304.05632","title":"Multi-agent Policy Reciprocity with Theoretical Guarantee","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2306.09742","title":"Meta Generative Flow Networks with Personalization for Task-Specific Adaptation","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2307.05834","title":"Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2308.07351","title":"IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2309.08776","title":"Projected Task-Specific Layers for Multi-Task Reinforcement Learning","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2401.12923","title":"Deep multitask neural networks for solving some stochastic optimal control problems","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2409.03149","title":"Non-stationary and Sparsely-correlated Multi-output Gaussian Process with Spike-and-Slab Prior","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2410.10006","title":"TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2412.20110","title":"Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification","created":"2024-12-28","cited_by_count":1,"area":null},{"id":"2503.20507","title":"Harmonia: Enhancing Data Placement and Migration in Hybrid Storage Systems via Multi-Agent Reinforcement Learning","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2505.23774","title":"On the Parallels Between Evolutionary Theory and the State of AI","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2512.09796","title":"Knowledge Diversion for Efficient Morphology Control and Policy Transfer","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2602.10891","title":"Interactive LLM-assisted Curriculum Learning for Multi-Task Evolutionary Policy Search","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2605.20085","title":"Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2304.06840","title":"Structured Pruning for Multi-Task Deep Neural Networks","created":"2023-04-13","cited_by_count":0,"area":null},{"id":"2310.17019","title":"Conditionally Combining Robot Skills using Large Language Models","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2311.12854","title":"Enhancing Robotic Manipulation: Harnessing the Power of Multi-Task Reinforcement Learning and Single Life Reinforcement Learning in Meta-World","created":"2023-10-23","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":"2406.11128","title":"Model Adaptation for Time Constrained Embodied Control","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2502.10027","title":"Heterogeneous Resource Allocation with Multi-task Learning for Wireless Networks","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2506.12891","title":"Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2507.20433","title":"FAST: Similarity-based Knowledge Transfer for Efficient Policy Learning","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2512.10891","title":"Iterative Compositional Data Generation for Robot Control","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.17923","title":"Learning Transferable Skills in Action RPGs via Directed Skill Graphs and Selective Adaptation","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2605.06111","title":"Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2610.20019","title":"MorphAct: Robot Policies Morphing with the Worlds They Act In","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}