search

duyminh1998 / pycmo

Command Modern Operations Learning Environment
Other
57 stars 25 forks source link

pycmo related inquiries(Can't progress beyond 50 steps) #63

Open rusmurf opened 9 months ago

rusmurf commented 9 months ago

I am playing with reference to your pycmo.

About the random agent, the number of steps cannot exceed 50, Have you tried solving this problem? (and the reason for this is believed to be an issue with storing up to 200 variables on the main function in Lua.)

Do you have experience performing more than 50 steps?

In the case of Q-learning agent, it appears to be a Q-learning algorithm rather than a code for CPE, so I would like to ask if you are interested in developing ML Agent.

duyminh1998 commented 9 months ago

Are you using the files in the scripts folder? Are you using the Steam or Professional version of Command? The only demo file that has a max step number of 50 is this. These files all run for more than 50 steps: floridistan and steam_demo.

I am interested in developing an RL agent for Command. It is just a very hard problem. I do not have a lot of experience working with a continuous state space. You are more than welcome to try!