InfoCoBuild

CS330 - Deep Multi-Task and Meta Learning

CS330: Deep Multi-Task and Meta Learning. Instructor: Prof. Chelsea Finn, Department of Computer Science and Electrical Engineering, Stanford University. While deep learning has achieved remarkable success in supervised and reinforcement learning problems, such as image classification, speech recognition, and game playing, these models are, to a large degree, specialized for the single task they are trained for. This course will cover the setting where there are multiple tasks to be solved, and study how the structure arising from multiple tasks can be leveraged to learn more efficiently or effectively. This includes:
• goal-conditioned reinforcement learning techniques that leverage the structure of the provided goal space to learn many tasks significantly faster
• meta-learning methods that aim to learn efficient learning algorithms that can learn new tasks quickly
• curriculum and lifelong learning, where the problem requires learning a sequence of tasks, leveraging their shared structure to enable knowledge transfer
This is a graduate-level course. By the end of the course, students will be able to understand and implement the state-of-the-art multi-task learning and meta-learning algorithms and be ready to conduct research on these topics. You can find more information about this course, such as lecture slides and syllabus, here. (from Stanfordonline)

Lecture 07 - Meta-RL, Learning to Explore (Kate Rakelly, UC Berkeley)


Go to the Course Home or watch other lectures:

Lecture 01 - Introduction and Overview
Lecture 02 - Multi-Task and Meta Learning Basics
Lecture 03 - Optimization-Based Meta Learning
Lecture 04 - Non-Parametric Meta Learners
Lecture 05 - Bayesian Meta Learning
Lecture 06 - Reinforcement Learning Primer
Lecture 07 - Meta-RL, Learning to Explore (Kate Rakelly, UC Berkeley)
Lecture 08 - Model-Based Reinforcement Learning
Lecture 09 - Lifelong Learning
Lecture 10 - Guest Lecture by Jeff Clune (Uber AI Labs)
Lecture 11 - Information Theoretic Exploration and Unsupervised Reinforcement Learning
Lecture 12 - Frontiers and Open Challenges
Lecture 13 - Student Literature Review 1
Lecture 14 - Student Literature Review 2