Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain
This addresses the problem of improving transfer learning efficiency for AI agents by preventing performance degradation and enabling targeted knowledge transfer, though it appears incremental as it builds on existing transfer learning methods.
The paper tackles the challenges of negative transfer and selective transfer in multi-source transfer learning by proposing A2T, an attentive deep architecture that adapts and transfers from source tasks, showing effectiveness in avoiding negative transfer and enabling selective transfer across different learning algorithms.
Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent should be able to avoid negative transfer, which happens when the transfer hampers or slows down the learning instead of helping it. Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task. We propose A2T (Attend, Adapt and Transfer), an attentive deep architecture which adapts and transfers from these source tasks. Our model is generic enough to effect transfer of either policies or value functions. Empirical evaluations on different learning algorithms show that A2T is an effective architecture for transfer by being able to avoid negative transfer while transferring selectively from multiple source tasks in the same domain.