-
The goal of this project is to help you get familiar with Unix com- mands and Python grammar.
-
In this project, your Pacman agent will find paths through his maze world, both to reach a particular location and to collect food efficiently. You will build general search algorithms and apply them to Pacman scenarios.
-
In this project, you will design agents for the classic version of Pacman, including ghosts. Along the way, you will implement both minimax and expectimax search and try your hand at evaluation function design.
-
In this project, you will implement value iteration and Q-learning. You will test your agents first on Gridworld (from class), then apply them to a simulated robot controller (Crawler) and Pacman.
-
A constraint satisfaction problem (CSP) is a problem whose solution is an assignment of values to variables that respects the constraints on the assignment and the variables’ domains.
CSPs are very powerful because a single fixed set of algorithms can be used to solve any problem specified as a CSP, and many problems can be intuitively specified as CSPs.
The goal of this project is to help you better understand CSPs and how they are solved. In this project you will be implementing a CSP solver and improving it with heuristic and inference algorithms.
-
In this project, you will design Pacman agents that use sensors to locate and eat invisible ghosts. You’ll advance from locating single, stationary ghosts to hunting packs of multiple moving ghosts with ruthless efficiency.
This course offers an overview and introduction to Artificial Intelligence: building blocks of intelligent systems (search, reasoning under certainty and uncertainty, decision-making, learning), some key algorithms, and their applications.
- Agents and environments
- Uninformed and informed Search
- Adversarial search and search under uncertainty
- Decision theory and game theory
- Markov decision process
- Reinforcement learning
- Constraint satisfaction problem
- Probability review
- Bayesian network
- Markov chain and hidden Markov models
- Generative approach in machine learning
- Discriminative approach in machine learning
- Neural networks
- Logical Agents
- Propositional logic
- First-order logic
- Classical planning