RLAIT

The Reinforcement Learning Artificial Intelligence Testbed

Goal

Develop an interface that can pair arbitrary reinforcement learning approaches to arbitrary tasks for better comparison and data collection.

Python (3.6+) + Keras + Tensorflow

The AlphaZero implementation is based off https://github.com/suragnair/alpha-zero-general. The Go implementation is based off https://github.com/davesque/go.py. Please check out @suragnair's and @davesque's amazing repos if you haven't already.

Name		Name	Last commit message	Last commit date
Latest commit History 62 Commits
az_checkpoints		az_checkpoints
ql_checkpoints		ql_checkpoints
rlait		rlait
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
alpha-zero-general-LICENSE		alpha-zero-general-LICENSE
go.py-LICENSE		go.py-LICENSE
main.py		main.py
requirements.txt		requirements.txt
run.py		run.py
run_othello4x4_qaz.py		run_othello4x4_qaz.py
run_othello6x6.py		run_othello6x6.py
run_stratego_alphazero.py		run_stratego_alphazero.py
run_stratego_rrtourney.py		run_stratego_rrtourney.py
run_uno.py		run_uno.py
setup_sample_stratego.txt		setup_sample_stratego.txt
t6x6-1.pkl		t6x6-1.pkl
t6x6-2.pkl		t6x6-2.pkl
t6x6-3.csv		t6x6-3.csv
t6x6-3.pkl		t6x6-3.pkl