Planning by Prioritized Sweeping with Small Backups
This work addresses computational bottlenecks in planning for reinforcement learning, offering a more flexible and efficient approach, though it is incremental in nature.
The paper tackles the computational inefficiency of traditional full backups in model-based reinforcement learning by introducing a new 'small backup' operation that uses only a single successor state, reducing computation time. They show that prioritized sweeping with small backups achieves substantial performance improvements over classical methods.
Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibit much finer control over their planning process than traditional methods. We empirically demonstrate that this increased flexibility allows for more efficient planning by showing that an implementation of prioritized sweeping based on small backups achieves a substantial performance improvement over classical implementations.