CS885 Module 1: Trust region & proximal policy optimization
The slides associated with this video are accessible on the course web: https://cs.uwaterloo.ca/~ppoupart/teaching/cs885-spring20/schedule.html
This video is part of a series of video lectures for CS885 offered by Pascal Poupart at the University of Waterloo in 2018 and 2020. Make sure to watch the previous video on trust region methods: https://youtu.be/qaOKZkeutqE
Видео CS885 Module 1: Trust region & proximal policy optimization канала Pascal Poupart
This video is part of a series of video lectures for CS885 offered by Pascal Poupart at the University of Waterloo in 2018 and 2020. Make sure to watch the previous video on trust region methods: https://youtu.be/qaOKZkeutqE
Видео CS885 Module 1: Trust region & proximal policy optimization канала Pascal Poupart
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
An introduction to Policy Gradient methods - Deep Reinforcement LearningCS885 Module 2: Maximum Entropy Reinforcement LearningCS885 Lecture 14c: Trust Region MethodsCS480/680 Lecture 19: Attention and Transformer NetworksCS885 Lecture 15b: Proximal Policy Optimization (Presenter: Ruifan Yu)Deep RL Bootcamp Lecture 5: Natural Policy Gradients, TRPO, PPOProximal Policy Optimization ExplainedAn Introduction to Proximal Policy Optimization (PPO) in Deep Reinforcement LearningCS885 Lecture 7b: Actor CriticTRPO (Trust Region Policy Optimization) : In depth Research Paper ReviewL4 TRPO and PPO (Foundations of Deep RL Series)Ensemble learnersCoRL 2020, Spotlight Talk 217: Sample-efficient Cross-Entropy Method for Real-time PlanningCS480/680 Lecture 11: Kernel MethodsProximal Policy Optimization is Easy with Tensorflow 2 | PPO TutorialIntro to Model-Free ControlCS885 Module 3: Imitation LearningTrust RegionsControl System Design with Observers and State Feedback