Policy Gradient: Optimal Estimation, Convergence, and Generalization beyond Cumulative Rewards

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=gRI4ZyHLGzc


Duration: 0:00
615 views
0

Mengdi Wang (Princeton University)
https://simons.berkeley.edu/talks/tbd-365
Adversarial Approaches in Machine Learning



Other Videos By Simons Institute for the Theory of Computing


2022-03-11The Impact of National Service on Beliefs, Mindsets, and Life Pathways...
2022-03-10Monitoring People and Their Vital Signs Using Radio Signals and Machine Learning
2022-03-08Causality and Autoencoders in Light of Drug Repurposing for COVID-19
2022-03-05Thinking Like a Journalist — Science Communicator in Residence Talk
2022-02-26Adversarial Machine Learning and Instrumental Variables for Flexible Causal Modeling
2022-02-26Online Adversarial Multicalibration And (Multi)Calibeating
2022-02-26Rebel: Combining Deep Reinforcement Learning and Search for Imperfect-Information Games
2022-02-26Generalized Energy-Based Models
2022-02-25Learning Uninformative Representations
2022-02-25Of Moments and Matching: Trade-offs and Treatments in Imitation Learning
2022-02-25Policy Gradient: Optimal Estimation, Convergence, and Generalization beyond Cumulative Rewards
2022-02-25Are Single-Loop Algorithms Sufficient for Unbalanced Minimax Optimization?
2022-02-25Zeroth-Order Methods for Convex-Concave Minmax Problems: Learning from Strategically Generated Data
2022-02-25Halpern Iteration and Equilibria Problems
2022-02-24Computationally Efficient Alternatives to Nonconvex-Nonconcave Min-Max Optimization
2022-02-16Balancing Covariates In Randomized Experiments: The Gram--Schmidt Walk Design
2022-02-16Some Staged Tree Models For Learning From Interventions
2022-02-16Learning And Testing Causal Models: A Property Testing Viewpoint
2022-02-16Panel Discussion
2022-02-16Machine Learning-Based Design Of Proteins
2022-02-15Searching For Causal Genetic Mechanisms Across Human Populations