Prioritized Sweeping
Description
Prioritized Sweeping is a reinforcement learning technique for model-based algorithms that prioritizes updates according to a measure of urgency, and performs these updates first. A queue is maintained of every state-action pair whose estimated value would change nontrivially if updated, prioritized by the size of the change. When the top pair in the queue is updated, the effect on each of its predecessor pairs is computed. If the effect is greater than some threshold, then the pair is inserted in the queue with the new priority.
Source: Sutton and Barto, Reinforcement Learning, 2nd Edition
Papers Using This Method
Investigating the Interplay of Prioritized Replay and Generalization2024-07-12Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping2020-01-15Reachability and Differential based Heuristics for Solving Markov Decision Processes2019-01-03Prioritized Sweeping Neural DynaQ with Multiple Predecessors, and Hippocampal Replays2018-02-15Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation2018-02-12Is prioritized sweeping the better episodic control?2017-11-20