Ian Rothstein
rothsteinian
ยท
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a dataset 1 day ago
andersonbcdefg/reward-modeling-long-tokenized upvoted a paper 1 day ago
Residual Transferability in Neural Image Watermarking liked a dataset 3 days ago
dynamicslab/HydroGym-OfflineRL-CacheOrganizations
None yet