Léo Martin
leo-mart
·
AI & ML interests
RLHF, RLAIF, offline RL, bandits
Recent Activity
liked a model about 9 hours ago
lobonexequiel/reinforcement-learning liked a model about 9 hours ago
Anandbheesetti/Lunar_Lander_By_using_reinforcement_learning upvoted a paper about 9 hours ago
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial IntelligenceOrganizations
None yet