Planning by Prioritized Sweeping with Small Backups

Abstract

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.

Cited by in corpus (10)

• Prioritized Experience Replay
• Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay
• One-shot learning and behavioral eligibility traces in sequential decision making
• Experience Replay with Likelihood-free Importance Weights
• Experience Replay Using Transition Sequences
• Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
• An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
• Is prioritized sweeping the better episodic control?
• Forethought and Hindsight in Credit Assignment
• Exploring Restart Distributions