Courses
Concepts
Explore
Playground
Practice
Log in
Course contents
← Back to course
Reinforcement Learning
You are in chapter 127
0% of course complete
127
Watson's Daily-Double Wagering Strategy
Module 2 · Why Self-Play Was Not Used
→
ARTICLE
Why Self-Play Was Not Used for Jeopardy! Wagering
›
Reinforcement Learning
›
Watson's Daily-Double Wagering Strategy
ARTICLE
Why Self-Play Was Not Used for Jeopardy! Wagering
Loading lesson…
← PREVIOUS
Risk Abatement Measures
MARK COMPLETE ✓
NEXT →
How Watson Learned Against Models of Human Opponents
