Open in app
Sign inGet started
Policy Certificates and Minimax-Optimal PAC Bounds for Episodic Reinforcement Learning

Policy Certificates and Minimax-Optimal PAC Bounds for Episodic Reinforcement Learning

Designing reinforcement learning methods which find a good policy with as few samples as possible is a key goal of both empirical and…
Go to the profile of Christoph Dann
Christoph Dann
Towards Reinforcement Learning Inspired By Humans Without Human Demonstrations

Towards Reinforcement Learning Inspired By Humans Without Human Demonstrations

Strategic Object Oriented Reinforcement Learning (SOORL)
Go to the profile of Ramtin Keramati
Ramtin Keramati
About Stanford AI for Human ImpactLatest StoriesArchiveAbout MediumTermsPrivacyTeams