Chidi Okafor
cokafor
ยท
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a dataset about 22 hours ago
open-source-metrics/reinforcement-learning-checkpoint-downloads liked a dataset about 22 hours ago
dynamicslab/HydroGym-OfflineRL-Cache upvoted a paper about 22 hours ago
MintAct: A Unified Visual Agent for Digital EnvironmentsOrganizations
None yet