Generalization in Reinforcement Learning with Selective Noise Injection

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=tWtM4Dq05ZA


Duration: 23:40
1,894 views
45

Reinforcement Learning Day 2019:
Generalization in Reinforcement Learning with Selective Noise Injection

See more at https://www.microsoft.com/en-us/research/video/generalization-in-reinforcement-learning-with-selective-noise-injection/



Other Videos By Microsoft Research


2019-10-24Microsoft PhD Summit 2019: Mike Sinclair [Short Talk]
2019-10-24Microsoft PhD Summit 2019: Siddharth Suri [Short Talk]
2019-10-24Microsoft PhD Summit 2019: Irene Zhang [Short Talk]
2019-10-24Microsoft PhD Summit 2019: Bailu Ding [Short Talk]
2019-10-24Microsoft PhD Summit 2019: Nathalie Riche [Short Talk]
2019-10-24Microsoft PhD Summit 2019: Ken Hinckley [Short Talk]
2019-10-24'The Global AI Supercomputer' by Donald Kossmann at Microsoft PhD Summit 2019 [Keynote]
2019-10-23Learning to Map Natural Language to General Purpose Source Code
2019-10-23Hand and User Detection with Multiple Users on Large Displays
2019-10-23Machine teaching, LUIS and the democratization of custom AI with Dr. Riham Mansour [Podcast]
2019-10-21Generalization in Reinforcement Learning with Selective Noise Injection
2019-10-21DreamWalker: Substituting Real-World Walking Experiences with a Virtual Reality
2019-10-21Learning Structured Models for Safe Robot Control
2019-10-21RDMA: Provably More Powerful Communication
2019-10-21Mise-Unseen: Using Eye Tracking to Hide Virtual Reality Scene Changes in Plain Sight
2019-10-21CapstanCrunch: A Haptic VR Controller with User-supplied Force Feedback
2019-10-18Social Computing for Social Good in Low-Resource Environments
2019-10-16News from the front in the post-quantum crypto wars with Dr. Craig Costello [Podcast]
2019-10-14Grounding Natural Language for Embodied Agents
2019-10-14Towards Using Batch Reinforcement Learning to Identify Treatment Options in Healthcare
2019-10-14Can quantum mechanics help us learn models of classical systems?


Tags:
Reinforcement Learning
RL Day 2019
Selective Noise Injection
Sam Devlin
microsoft research