aref81/berkeley-ai-cs-188-project

Artificial Intelligence Course - Amirkabir University of Technology - Adapted From Berkeley-CS188 (Spring 2023)

• Project 1: Search
• Project 2: Multiagent
• Project 3: Reinforcement Learning

Project 1: Search

Implementation of DFS (Depth First Search), BFS (Breadth First Search), UCS (Uniform Cost Search) and A* search with differente heuristics. this search algorithms are used for pacman path-finding problem.

Provisional grades
==================
Question q1: 3/3
Question q2: 3/3
Question q3: 3/3
Question q4: 3/3
Question q5: 3/3
Question q6: 3/3
Question q7: 5/4
Question q8: 3/3
------------------
Total: 26/25

Project 2: Multiagent

Implementation of Minimax, Alpha-Beta Pruning and Expectimax and differente cost-estimating functions. using this implementetion, pacman could act fairly well in game.

Provisional grades
==================
Question q1: 4/4
Question q2: 5/5
Question q3: 5/5
Question q4: 5/5
Question q5: 6/6
------------------
Total: 25/25

Project 3: Reinforcement Learning

Implemention of RL and Q-Learning agent to solve a variation of problems, such as maze solving, crawling robot and pacman.

Provisional grades
==================
Question q1: 4/4
Question q2: 1/1
Question q3: 5/5
Question q4: 1/1
Question q5: 3/3
Question q6: 4/4
Question q7: 2/2
Question q8: 1/1
Question q9: 1/1
Question q10: 3/3
------------------
Total: 25/25