Explore reinforcement learning concepts in this comprehensive lecture from CMU's Neural Networks for NLP course. Delve into the fundamentals of reinforcement learning, policy gradient methods, and the REINFORCE algorithm. Learn techniques for stabilizing reinforcement learning and understand value-based approaches. Access accompanying slides and code examples to reinforce your understanding. Gain insights into practical applications of reinforcement learning in natural language processing, including dialogue systems and user simulators. Discover the differences between supervised learning and self-training, and explore the challenges of credit assignment and exploration vs. exploitation in reinforcement learning scenarios.
Overview
Syllabus
Intro
What is reinforcement learning
Examples of reinforcement learning
Supervised Learning
Self Training
Policy Gradient
Credit assignment
Problem
Baseline
Calculating the baseline
Increasing batch size
Reinforcement Learning
Runthrough
Valuebased reinforcement learning
Estimating value functions
Exploration vs exploitation
Reinforcement learning examples
Dialogue
User simulators
Actions in spaces
Taught by
Graham Neubig
Related Courses
-
Neural Nets for NLP 2019 - Reinforcement Learning
-
Neural Nets for NLP - Minimum Risk Training and Reinforcement Learning
-
Neural Nets for NLP 2017 - Unsupervised Learning of Structure
-
Reinforcement Learning - Part I
-
Neural Nets for NLP 2017 - Multilingual and Multitask Learning
-
Backpropagation and Deep Learning in the Brain
