Disputationer

Improving Sample-efficiency of Reinforcement Learning from Human Feedback

1 apr

Disputationer

Datalogi

tisdag 2025-04-01, 14.00

Plats: F3 (Flodis), Lindstedtsvägen 26

Videolänk: https://kth-se.zoom.us/j/62755931085

Respondent: Simon Holk , Robotik, perception och lärande, RPL

2025-04-01T14:00:00.000+02:00 2025-04-01T14:00:00.000+02:00 Improving Sample-efficiency of Reinforcement Learning from Human Feedback (Disputationer) F3 (Flodis), Lindstedtsvägen 26 (KTH, Stockholm, Sweden)Improving Sample-efficiency of Reinforcement Learning from Human Feedback (Disputationer)