ARotting
/

microzero

Reinforcement Learning

monte-carlo-tree-search

policy-value-network

Model card Files Files and versions

microzero / source /requirements.txt

ARotting's picture

Publish 7.6K parameter neural MCTS self-play agent

c80bb82 verified 3 days ago

History Blame Contribute Delete

59 Bytes

	gradio>=5,<7
	numpy>=2,<3
	safetensors>=0.6,<1
	torch>=2.7,<3