TRPO

Software / App

Trust Region Policy Optimization, an off-policy RL algorithm that takes multiple steps while staying close to the original policy using importance weighting corrections.

Mentioned in 1 video

Videos Mentioning TRPO

Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 15: Mid/Post-Training

Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 15: Mid/Post-Training

Stanford Online

Trust Region Policy Optimization, an off-policy RL algorithm that takes multiple steps while staying close to the original policy using importance weighting corrections.