#RLHF

Robot Learning from Human Demonstration: Current State and Benchmarks

A survey of robot learning from human demonstration covering imitation learning algorithms, the distribution shift problem, and leading benchmarks like CALVIN, RLBench, and OpenVLA.

How Reinforcement Learning from Human Feedback Is Reshaping Robotic Manipulation in 2026

RLHF vs RLAIF: Comparing Human Feedback and AI Feedback for LLM Alignment

A practical comparison of RLHF and RLAIF for LLM alignment in 2026. Cost benchmarks, quality trade-offs, and a decision framework for ML practitioners.