Article Source

• Title: Deep RL Bootcamp Lecture 5: Natural Policy Gradients, TRPO, PPO

Natural Policy Gradients, TRPO, PPO

• Instructor: John Schulman (OpenAI)
• Program: Lecture 5 Deep RL Bootcamp Berkeley August 2017
• Title: Natural Policy Gradients, TRPO, PPO

TPRO Paper Review