Reward Machines: Structuring Reward Function Specifications and Reducing Sample Complexity...

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=0wYeJAAnGl8


Duration: 45:21
5,244 views
145

Reinforcement Learning Day 2019:
Reward Machines: Structuring Reward Function Specifications and Reducing Sample Complexity in Reinforcement Learning

See more at https://www.microsoft.com/en-us/research/video/reward-machines-structuring-reward-function-specifications-and-reducing-sample-complexity-in-rl/



Other Videos By Microsoft Research


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?
2019-10-14Reinforcement Learning From Small Data in Feature Space
2019-10-14Reward Machines: Structuring Reward Function Specifications and Reducing Sample Complexity...
2019-10-14Structure Visual Understanding and Interaction with Human and Environment
2019-10-14Improving Doctor-Patient Interaction with ML-Enabled Clinical Note Taking
2019-10-11HapSense: A Soft Haptic I/O Device with Uninterrupted Dual Functionalities...
2019-10-09Advanced polarized light microscopy for mapping molecular orientation
2019-10-09Data science and ML for human well-being with Jina Suh [Podcast]
2019-10-07Tea: A High-level Language and Runtime System for Automating Statistical Analysis [Python module]
2019-10-07Discover[i]: Component-based Parameterized Reasoning for Distributed Applications
2019-10-04Scheduling For Efficient Large-Scale Machine Learning Training
2019-10-03Distributed Entity Resolution for Computational Social Science
2019-10-03MMLSpark: empowering AI for Good with Mark Hamilton [Podcast]


Tags:
RL Day 2019
reinforcement learning
reward machines
MSR New York
microsoft research
Sheila Mcllraith