Completed
Estimating Value Functions
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP - Minimum Risk Training and Reinforcement Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Problem 1: Exposure Bias
- 3 Problem 2: Disregard to Evaluation Metrics
- 4 Error
- 5 Problem: Argmax is Non- differentiable
- 6 Sampling for Risk
- 7 Adding Temperature
- 8 What is Reinforcement Learning?
- 9 Why Reinforcement Learning in NLP?
- 10 Supervised MLE
- 11 Self Training
- 12 Policy Gradient/REINFORCE
- 13 Credit Assignment for Rewards
- 14 Problems w/ Reinforcement Learning
- 15 Adding a Baseline
- 16 Calculating Baselines
- 17 Increasing Batch Size
- 18 Warm-start
- 19 When to Use Reinforcement Learning?
- 20 Action-Value Function
- 21 Estimating Value Functions
