Defines Markov decision processes, stochastic transitions, rewards, policies, and discounted utility, with gridworld and racing examples.
Save to open this file
Berkeley CS188: Introduction to Artificial Intelligence
All
- 01-Intro
01-Intro
- 02-Uninformed Search
- 03-A* Search and Heuristics
- 04-CSPs I
- 05-CSPs II
- 06-Game Trees I
- 07-Game Trees II
- 08-MDPs I
- 09-MDPs II
- 10-RL I
- 11-RL II
- 12-Probability
- 13-Bayes Nets: Representation
- 14-Bayes Nets: Independence
- 15-Bayes Nets: Inference
- 16-Bayes Nets: Sampling
- 17-Decision Networks and VPI
- 18-HMMs
- 19-Particle Filtering
- 20-ML I: Naive Bayes
- 21-ML II: Perceptrons
- 22-ML III: Neural Networks
- 23-ML IV: Applications & Decision Trees
- 24-ML V: Transformers
- 25-Applications: AI for Healthcare
- 26-Applications: AI for Equality and Course Wrap-up