Attentive Multi-Task Deep Reinforcement Learning
This addresses the challenge of harmful interference between tasks in multi-task learning, which is crucial for efficient AI systems in complex environments.
The paper tackles the problem of negative knowledge transfer in multi-task deep reinforcement learning by introducing an attention-based method that automatically groups task knowledge into sub-networks, achieving comparable or superior performance to state-of-the-art approaches with fewer parameters.
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.