-
It's a simple&naive platform for multiagent chainMDP problem.
-
The algorithm now used: DDQN+reward updated.
-
Environment needed:
python3.5, Tensorflow1.4.0, Numpy1.13.3, matplotlib2.1.0, Tensorboard0.4.0rc(unnecessary) -
Both GPU or CPU for tensorflow are surpported.
-
References:
-
Need to be done:
- Multi thread to speed up
- More algorithm should be applied
- A more efficient exploration method to solve it.
-
Notifications
You must be signed in to change notification settings - Fork 1
CoffeeddCat/Multiagent_chainMDP
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A simple&naive platform for multiagent chainMDP problem.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published