# Multi-Task Reinforcement Learning with Soft Modularization

arXiv: https://arxiv.org/abs/2003.13661 · HTML: https://mlsanity.com/paper/2003.13661/

## Key facts

- Cited by 143 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 30 of 143)

- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2305.18459/) (2023)
- [GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields](https://mlsanity.com/paper/2308.16891/) (2023)
- [Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention](https://mlsanity.com/paper/2104.11203/) (2021)
- [FAMO: Fast Adaptive Multitask Optimization](https://mlsanity.com/paper/2306.03792/) (2023)
- [Independent Component Alignment for Multi-Task Learning](https://mlsanity.com/paper/2305.19000/) (2023)
- [Conservative Data Sharing for Multi-Task Offline Reinforcement Learning](https://mlsanity.com/paper/2109.08128/) (2021)
- [Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning](https://mlsanity.com/paper/2302.11289/) (2023)
- [Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts](https://mlsanity.com/paper/2311.11385/) (2023)
- [DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets](https://mlsanity.com/paper/2404.19264/) (2024)
- [PaCo: Parameter-Compositional Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2210.11653/) (2022)
- [Meta-World+: An Improved, Standardized, RL Benchmark](https://mlsanity.com/paper/2505.11289/) (2025)
- [Modular Lifelong Reinforcement Learning via Neural Composition](https://mlsanity.com/paper/2207.00429/) (2022)
- [The Neural Race Reduction: Dynamics of Abstraction in Gated Networks](https://mlsanity.com/paper/2207.10430/) (2022)
- [Lifelong Robotic Reinforcement Learning by Retaining Experiences](https://mlsanity.com/paper/2109.09180/) (2021)
- [Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms](https://mlsanity.com/paper/2305.18409/) (2023)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning](https://mlsanity.com/paper/2207.04703/) (2022)
- [LLM-Empowered State Representation for Reinforcement Learning](https://mlsanity.com/paper/2407.13237/) (2024)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems](https://mlsanity.com/paper/2111.04613/) (2021)
- [Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training](https://mlsanity.com/paper/2402.14407/) (2024)
- [Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments](https://mlsanity.com/paper/2201.00042/) (2021)
- [Universal Morphology Control via Contextual Modulation](https://mlsanity.com/paper/2302.11070/) (2023)
- [DNAct: Diffusion Guided Multi-Task 3D Policy Learning](https://mlsanity.com/paper/2403.04115/) (2024)
- [CompoSuite: A Compositional Reinforcement Learning Benchmark](https://mlsanity.com/paper/2207.04136/) (2022)

## Abstract (arXiv)

Multi-task learning is a very challenging problem in reinforcement learning. While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across tasks, and how the gradients from different tasks may interfere with each other. Thus, instead of naively sharing parameters across tasks, we introduce an explicit modularization technique on policy representation to alleviate this optimization issue. Given a base policy network, we design a routing network which estimates different routing strategies to reconfigure the base network for each task. Instead of directly selecting routes for each task, our task-specific policy uses a method called soft modularization to softly combine all the possible routes, which makes it suitable for sequential tasks. We experiment with various robotics manipulation tasks in simulation and show our method improves both sample efficiency and performance over strong baselines by a large margin.