Reinforcement Learning 6: Policy Gradients and Actor Critics

Channel:
United Kingdom Google DeepMind
Subscribers:
487,000
Published on ● Video Link: https://www.youtube.com/watch?v=bRfUxQs6xIM


Duration: 1:34:41
77,779 views
875

Hado Van Hasselt, Research Scientist, discusses policy gradients and actor critics as part of the Advanced Deep Learning & Reinforcement Learning Lectures.



Other Videos By Google DeepMind


2020-03-04Life is like a game - DeepMind: The Podcast (S1, Ep3)
2020-03-04Go to Zero - DeepMind: The Podcast (S1, Ep2)
2020-03-04AI and neuroscience: The virtuous circle - DeepMind: The Podcast (S1, Ep1)
2019-11-26DeepMind Scholars: Shaquille's story
2019-08-20DeepMind: The Podcast (S1 trailer)
2019-04-08The Power of Self-Learning Systems
2019-01-31Game highlights of AlphaStar versus Team Liquid’s TLO and MaNa
2019-01-24DeepMind StarCraft II Demonstration
2019-01-24AlphaStar: The inside story
2018-12-06AlphaZero: Shedding new light on the grand games of chess, shogi and Go
2018-11-23Reinforcement Learning 6: Policy Gradients and Actor Critics
2018-11-23Reinforcement Learning 10: Classic Games Case Study
2018-11-23Reinforcement Learning 9: A Brief Tour of Deep RL Agents
2018-11-23Deep Learning 4: Beyond Image Recognition, End-to-End Learning, Embeddings
2018-11-23Deep Learning 7. Attention and Memory in Deep Learning
2018-11-23Deep Learning 6: Deep Learning for NLP
2018-11-23Deep Learning 3: Neural Networks Foundations
2018-11-23Deep Learning 5: Optimization for Machine Learning
2018-11-23Deep Learning 8: Unsupervised learning and generative models
2018-11-23Reinforcement Learning 1: Introduction to Reinforcement Learning
2018-11-23Deep Learning 2: Introduction to TensorFlow