Skip to content

Latest commit

 

History

History
46 lines (24 loc) · 1.45 KB

README.md

File metadata and controls

46 lines (24 loc) · 1.45 KB
Raw

CZ4046 : Intelligent Agents

Learning Outcome

I have learnt fundamentals in reinforcement learning (RL) and the two RL algorithms such as Value Iteration and Policy Iteraiton. I have also gained knowledge regarding Individual/Single Agent as well as Multi-Agent System (MAS). The coursework includes two assignments :

  1. Implementing Value Iteration and Policy Iteration algorithms to find the optimal policy for a given maze environment
  2. Implementing Repeated Prisoners' Dilemma (the scenario involving three players)

Coursework Assignments

Assignment 1: Implemented Value Iteration and Policy Iteration by using Java code in order to find the best policy for a given maze environment

Assignment 2: Implemented a player class to compete with other players by using java code in the scenario, Repeated Prisoners' Dilemma.

Please refer to the two assignment/project reports for more details.

Disclaimer : The Java code used to build the coursework assignments is no longer maintained. There may be errors or bugs that did not exist at the time of creation.

Knowledge Accquired includes:

  1. Introduction to Intelligent Agents

  2. Deductive Reasoning Agents

  3. Practical Reasoning Agents

  4. Reactive and Hybrid Architectures

  5. Introduction to Multi-Agent Systems and Applications

  6. Working Together

  7. Multi-Agent Interaction

  8. Allocating Scarce Resources – Auctions

  9. Making Group Decisions

  10. Forming Coalitions