iluman
/

guandan-ai

Reinforcement Learning

deep-monte-carlo

Model card Files Files and versions

guandan-ai / models

254 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

iluman's picture

Add V8 Phase 2b Step 850K (64% vs Champion, 74.5% vs V1)

79f5962 verified about 1 month ago

v8_best_step3810k_wr585.onnx

84.6 MB
xet

V8 best checkpoint (58.5% vs Champion, 72% vs V1) — ONNX format about 1 month ago
v8p2b_best_step850k_wr640.onnx

84.6 MB
xet

Add V8 Phase 2b Step 850K (64% vs Champion, 74.5% vs V1) about 1 month ago
v8p2b_best_wr625.onnx

84.6 MB
xet

V8 Phase2b best (62.5% vs Champion, 73% vs V1) about 1 month ago