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

4 July 2021

Gal Dalal

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

3 / 3 papers shown

Title
The Effective Horizon Explains Deep RL Performance in Stochastic Environments Cassidy Laidlaw Banghua Zhu Stuart J. Russell Anca Dragan 8 2 0 13 Dec 2023
Planning and Learning with Adaptive Lookahead Aviv A. Rosenberg Assaf Hallak Shie Mannor Gal Chechik Gal Dalal 11 7 0 28 Jan 2022
Beyond the One Step Greedy Approach in Reinforcement Learning Yonathan Efroni Gal Dalal B. Scherrer Shie Mannor OffRL 33 48 0 10 Feb 2018