DeepMind x UCL RL Lecture Series - Multi-step & Off Policy [11/13]

Channel:
United Kingdom Google DeepMind
Subscribers:
663,000
Published on ● Video Link: https://www.youtube.com/watch?v=u84MFu1nG4g


Duration: 1:32:30
11,321 views
136

Research Scientist Hado van Hasselt discusses multi-step and off policy algorithms, including various techniques for variance reduction.

Slides: https://dpmd.ai/offpolicy
Full video lecture series: https://dpmd.ai/DeepMindxUCL21



Other Videos By Google DeepMind


2021-09-09DeepMind x UCL RL Lecture Series - Introduction to Reinforcement Learning [1/13]
2021-09-09DeepMind x UCL RL Lecture Series - Exploration & Control [2/13]
2021-09-09DeepMind x UCL RL Lecture Series - MDPs and Dynamic Programming [3/13]
2021-09-09DeepMind x UCL RL Lecture Series - Theoretical Fund. of Dynamic Programming Algorithms [4/13]
2021-09-09DeepMind x UCL RL Lecture Series - Model-free Prediction [5/13]
2021-09-09DeepMind x UCL RL Lecture Series - Model-free Control [6/13]
2021-09-09DeepMind x UCL RL Lecture Series - Function Approximation [7/13]
2021-09-09DeepMind x UCL RL Lecture Series - Planning & models [8/13]
2021-09-09DeepMind x UCL RL Lecture Series - Policy-Gradient and Actor-Critic methods [9/13]
2021-09-09DeepMind x UCL RL Lecture Series - Approximate Dynamic Programming [10/13]
2021-09-09DeepMind x UCL RL Lecture Series - Multi-step & Off Policy [11/13]
2021-09-09DeepMind x UCL RL Lecture Series - Deep Reinforcement Learning #1 [12/13]
2021-09-09DeepMind x UCL RL Lecture Series - Deep Reinforcement Learning #2 [13/13]
2021-07-27Open-Ended Learning Leads to Generally Capable Agents | Results Showreel
2021-07-22AlphaFold Protein Structure Database
2021-01-05NeurIPS 2020: JAX Ecosystem Meetup
2020-11-30AlphaFold: The making of a scientific breakthrough
2020-11-30Protein folding explained
2020-11-05DeepMind Scholars: Benedetta's story
2020-07-09DeepMind x UCL | Deep Learning Lectures | 12/12 | Responsible Innovation
2020-07-09DeepMind x UCL | Deep Learning Lectures | 11/12 | Modern Latent Variable Models