We applied Q-learning, the process of learning the value of state-action pairs, to games where the full state is not surfaced to the decision maker. Our full results are described here, but, in summary, we determined that a Q-learning agent could eventually understand the likelihood of various world states given the surfaced state and act accordingly.
ryanholmdahl/qlearn
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Q-learning on Games of Imperfect Information
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published