Skip to content

Latest commit

 

History

History
8 lines (8 loc) · 250 Bytes

File metadata and controls

8 lines (8 loc) · 250 Bytes
  • Game strategy learning with Reinforcement Learning framework
  • Task: minimize game play time and maximize profits
  • Learning methods: Rule based Linear Function Approximation Feed-forward Neural Network SARSA
  • Language: MatLab/C++