# Attentive Multi-Task Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1907.02874 · HTML: https://mlsanity.com/paper/1907.02874/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [Improving Policy Optimization with Generalist-Specialist Learning](https://mlsanity.com/paper/2206.12984/) (2022)
- [Multi-Environment Pretraining Enables Transfer to Action Limited Datasets](https://mlsanity.com/paper/2211.13337/) (2022)
- [Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning](https://mlsanity.com/paper/2102.09361/) (2021)
- [Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour](https://mlsanity.com/paper/2106.01434/) (2021)
- [Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction](https://mlsanity.com/paper/2404.05950/) (2024)
- [PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent](https://mlsanity.com/paper/2202.00531/) (2022)
- [Multi-Task Learning for User Engagement and Adoption in Live Video Streaming Events](https://mlsanity.com/paper/2106.10305/) (2021)

## Abstract (arXiv)

Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach to multi-task deep reinforcement learning based on attention that does not require any a-priori assumptions about the relationships between tasks. Our attention network automatically groups task knowledge into sub-networks on a state level granularity. It thereby achieves positive knowledge transfer if possible, and avoids negative transfer in cases where tasks interfere. We test our algorithm against two state-of-the-art multi-task/transfer learning approaches and show comparable or superior performance while requiring fewer network parameters.