Publikation
Sharing Knowledge in Multi-Task Deep Reinforcement Learning
Carlo D'Eramo; Davide Tateo; Andrea Bonarini; Marcello Restelli; Jan Peters
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2401.09561, Pages 1-18, arXiv, 2024.
Zusammenfassung
We study the benefit of sharing representations among tasks to enable the effective
use of deep neural networks in Multi-Task Reinforcement Learning. We leverage
the assumption that learning from different tasks, sharing common properties, is
helpful to generalize the knowledge of them resulting in a more effective feature ex-
traction compared to learning a single task. Intuitively, the resulting set of features
offers performance benefits when used by Reinforcement Learning algorithms.
We prove this by providing theoretical guarantees that highlight the conditions
for which is convenient to share representations among tasks, extending the well-
known finite-time bounds of Approximate Value-Iteration to the multi-task setting.
In addition, we complement our analysis by proposing multi-task extensions of
three Reinforcement Learning algorithms that we empirically evaluate on widely
used Reinforcement Learning benchmarks showing significant improvements over
the single-task counterparts in terms of sample efficiency and performance.