AlphaGo_Zero

AlphaGo Zero is a version of DeepMind Go software AlphaGo. It is trained solely by self-play reinforcement learning. It uses a simpler tree search that relies upon single neural network, without performing any Monte Carlo rollouts.
# Black player White player Result Event Game date uploader
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+1.50 AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+1.50 AlphaGo_Zero
AlphaGo Zero AlphaGo Lee B+Resign AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+0.50 AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+0.50 AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero
AlphaGo Lee AlphaGo Zero W+R AlphaGo_Zero