Copter_works_point05

remixed by gsetRL
  scripts
  sprites
See inside
Notes and Credits (added by gsetRL)

This is a reinforcement learning demo version of Copter which uses a Q learning algorithm to control the helicopter, assigning negative rewards for hitting the walls and ceilings. The environment is described using four variables, which define the copter's position with relation to the walls and the floor/ceiling. This version has saved variable values after learning over thousands of steps, so you can watch it use what it has learned to navigate the environment!

Shared: 30 Jul 2009 Modified: 30 Jul 2009
Favorite this project 0
Love this project 0
Total views 97
View the remix tree  25
  
More projects by gsetRL