Attentive Multi-Task Deep Reinforcement Learning
By Timo Bram, Gino Brunner, Oliver Richter, Roger Wattenhofer. 2019
19 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Qiang Yang
- Joelle Pineau
- Yu Zhang
- Amy Zhang
- Shagun Sodhani
- Mingsheng Long
- Sergey Levine
- Jianmin Wang
Citations in the corpus
- A Survey on Multi-Task Learning (2017, methodology): “In [148], a multi-task deep RL model based on the attention can automatically group tasks into sub-networks on a state-level granularity.”
- Multi-Task Reinforcement Learning with Context-based Representations (2021, background): “(Br¨am et al., 2019) considered the setup when the action space between different tasks is not aligned.”