Generalizing the Projected Bellman Error Objective for Nonlinear Value Estimation
Martha White (University of Alberta)
https://simons.berkeley.edu/talks/tbd-223
Deep Reinforcement Learning
Видео Generalizing the Projected Bellman Error Objective for Nonlinear Value Estimation канала Simons Institute
https://simons.berkeley.edu/talks/tbd-223
Deep Reinforcement Learning
Видео Generalizing the Projected Bellman Error Objective for Nonlinear Value Estimation канала Simons Institute
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Off-policy Policy OptimizationFast Reinforcement Learning With Generalized Policy UpdatesNonparametric Bayesian Methods: Models, Algorithms, and Applications IPolicy Gradients Methods, Neural Policy Classes, and Distribution ShiftWhat's a Tensor?The Unreasonable Effectiveness of Spectral Graph Theory: A Confluence of Algorithms, Geometry & ...Stabilizing Q-learning with Weighted Bellman LossesAgile EstimationStatQuest: R-squared explainedAdventures in Linear Algebra++ and Unsupervised LearningHigh-Dimensional Statistics IPC-PG: Policy Cover Directed Exploration for Provable Policy Gradient LearningAnalysis of Probabilistic Systems IThe Effectiveness of Convex Programming in the Information and Physical SciencesLearn agile estimation in 10 minutesDiscussion: ExplorationVariational Inference: Foundations and InnovationsComputational Challenges and the Future of ML PanelSpanish For Beginners | Spanish 101 (Ep.1)