Skip to content

Latest commit

 

History

History
15 lines (13 loc) · 577 Bytes

README.md

File metadata and controls

15 lines (13 loc) · 577 Bytes

Reinforcement Learning

Reinforcement Learning Experiments

TicTacToe_Numerical_Game

  • This is a RL agent with can play numerical TicTacToe.
  • This game has a 3X3 GRID as a playground.
  • One player gets even numbers {2,4,6,8}
  • Other get odd numbers {1,3,5,7,9}.
  • Objective :
    • A player wins when he/she is able to attain a SUM of 15 in any row/column or major diagonals.
    • Look for more details in repo directory

RL Based Cab Driver Ride Selection

  • A model for cab drivers to select appropriate rides suggested by a hypothetical city map.
  • (To be updated)