← Search

Steven Dalton

2 accepted papers

2021

Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction

NeurIPS 2021poster

Tree Search (TS) is crucial to some of the most influential successes in reinforcement learning. Here, we tackle two major challenges with TS that limit its usability: \textit{distribution shift} and \textit{scalability}. We first discover and analyze a counter-intuitive phenomenon: action selection…