Hierarchical Imitation Learning with Vector Quantized Models
Offered By: Finnish Center for Artificial Intelligence FCAI via YouTube
Course Description
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore hierarchical imitation learning with vector quantized models in this 51-minute talk by Alexander Ilin from the Finnish Center for Artificial Intelligence (FCAI). Discover how intelligent agents can effectively solve complex tasks by planning actions on multiple levels of abstraction. Learn about a novel approach that uses reinforcement learning to identify subgoals in expert trajectories, associating reward magnitude with the predictability of low-level actions. Examine the vector-quantized generative model for subgoal-level planning and its application in complex, long-horizon decision-making problems. Understand how this algorithm outperforms state-of-the-art methods and can find better trajectories than those in the training set. Gain insights from Alexander Ilin, a Professor of Practice at Aalto University, whose research focuses on deep representation learning and model-based reinforcement learning.
Syllabus
Alexander Ilin: Hierarchical Imitation Learning with Vector Quantized Models
Taught by
Finnish Center for Artificial Intelligence FCAI
Related Courses
Deep Learning and Python Programming for AI with Microsoft AzureCloudswyft via FutureLearn Advanced Artificial Intelligence on Microsoft Azure: Deep Learning, Reinforcement Learning and Applied AI
Cloudswyft via FutureLearn Overview of Advanced Methods of Reinforcement Learning in Finance
New York University (NYU) via Coursera AI for Cybersecurity
Johns Hopkins University via Coursera 人工智慧:機器學習與理論基礎 (Artificial Intelligence - Learning & Theory)
National Taiwan University via Coursera