Sharing Knowledge in Multi-Task Deep Reinforcement Learning
This work addresses sample efficiency and performance in multi-task reinforcement learning, offering incremental advances with theoretical and empirical support.
The paper tackles the problem of improving multi-task deep reinforcement learning by sharing representations among tasks, proving theoretical conditions for benefit and showing empirical improvements in sample efficiency and performance over single-task methods.
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 extraction 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.