RL+LLM Wiki

AI & ML interests

None defined yet.

Recent Activity

kshitijthakkar  new activity about 2 hours ago

rl-llm-wiki/knowledge-base:source: arxiv:2301.11270 - Principled RLHF (Zhu-Jordan-Jiao: MLE converges but its policy fails; pessimistic MLE minimax-optimal; K-wise splitting consistent but inefficient)

kshitijthakkar  updated a bucket about 2 hours ago

rl-llm-wiki/rl-chiku-inu

kshitijthakkar  new activity about 3 hours ago

rl-llm-wiki/knowledge-base:source: arxiv:2607.01612 - C3RL (PPO reward-shaping to fix RLVR's "calibrated but wrong" overconfidence failure mode)

View all activity

Team members 7