← Search

Thomas K Hubert

2 accepted papers

2022

Planning in Stochastic Environments with a Learned Model

ICLR 2022spotlight

Model-based reinforcement learning has proven highly successful. However, learning a model in isolation from its use during planning is problematic in complex environments. To date, the most effective techniques have instead combined value-equivalent model learning with powerful tree-search methods.…

Cited by 85SourcePDFScholar
2021

Online and Offline Reinforcement Learning by Planning with a Learned Model

NeurIPS 2021spotlight

Learning efficiently from small amounts of data has long been the focus of model-based reinforcement learning, both for the online case when interacting with the environment, and the offline case when learning from a fixed dataset. However, to date no single unified algorithm could demonstrate state…

Cited by 138SourcePDFScholar