{"total":22,"rows":[{"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":"2102.02915","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":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116,"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":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2206.12984","title":"Improving Policy Optimization with Generalist-Specialist Learning","created":"2022-06-26","cited_by_count":20,"area":null},{"id":"2405.15815","title":"A social path to human-like artificial intelligence","created":"2024-05-22","cited_by_count":20,"area":null},{"id":"2512.20607","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","created":"2025-12-23","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":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2107.11587","title":"Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?","created":"2021-07-24","cited_by_count":11,"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":"2402.04005","title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2503.24322","title":"NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation","created":"2025-03-31","cited_by_count":8,"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":"2603.12151","title":"IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL","created":"2026-03-12","cited_by_count":6,"area":null},{"id":"2307.04887","title":"Measuring and Mitigating Interference in Reinforcement Learning","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2302.04693","title":"Scaling Goal-based Exploration via Pruning Proto-goals","created":"2023-02-09","cited_by_count":2,"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":"2402.03557","title":"Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement","created":"2024-02-05","cited_by_count":1,"area":null}],"next_cursor":null}