Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity
Dec 6, 2020
Speakers
Simon S. Du
Speaker · 3 followers
Ruosong Wang
Speaker · 0 followers
Jason D. Lee
Speaker · 1 follower
Organizer
NeurIPS 2020
Account · 11.6k followers
Categories
AI & Data Science
Category · 10.8k presentations
Mathematics
Category · 2.4k presentations
About NeurIPS 2020
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Meta-trained agents implement Bayes-optimal agents
Watch later
Vlad Mikulik, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
MetaPoison: Practical General-purpose Clean-label Data Poisoning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Neural Networks Fail to Learn Periodic Functions and How to Fix It
Watch later
Ziyin Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Challenging common interpretability assumptions in feature attribution explanations
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Diversity can be Transferred: Output Diversification for White- and Black-box Attacks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%