| { | |
| "model": "MicroZero", | |
| "parameters": 7626, | |
| "self_play_iterations": 14, | |
| "self_play_games": 980, | |
| "final_replay_examples": 24000, | |
| "training_history": [ | |
| { | |
| "iteration": 1, | |
| "replay_examples": 4128, | |
| "x_win_rate": 0.5428571428571428, | |
| "o_win_rate": 0.14285714285714285, | |
| "draw_rate": 0.3142857142857143, | |
| "average_game_moves": 7.371428571428571, | |
| "policy_loss": 2.1499555636854732, | |
| "value_loss": 0.5162482239744243 | |
| }, | |
| { | |
| "iteration": 2, | |
| "replay_examples": 8128, | |
| "x_win_rate": 0.5142857142857142, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.4857142857142857, | |
| "average_game_moves": 7.142857142857143, | |
| "policy_loss": 1.9038925133645535, | |
| "value_loss": 0.3203776921145618 | |
| }, | |
| { | |
| "iteration": 3, | |
| "replay_examples": 12328, | |
| "x_win_rate": 0.42857142857142855, | |
| "o_win_rate": 0.014285714285714285, | |
| "draw_rate": 0.5571428571428572, | |
| "average_game_moves": 7.5, | |
| "policy_loss": 1.4543613067695074, | |
| "value_loss": 0.26955098012576295 | |
| }, | |
| { | |
| "iteration": 4, | |
| "replay_examples": 16456, | |
| "x_win_rate": 0.5142857142857142, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.4857142857142857, | |
| "average_game_moves": 7.371428571428571, | |
| "policy_loss": 1.229265012878638, | |
| "value_loss": 0.22285609325537314 | |
| }, | |
| { | |
| "iteration": 5, | |
| "replay_examples": 20952, | |
| "x_win_rate": 0.2857142857142857, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.7142857142857143, | |
| "average_game_moves": 8.028571428571428, | |
| "policy_loss": 1.1138035529633847, | |
| "value_loss": 0.1854344406960214 | |
| }, | |
| { | |
| "iteration": 6, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.3142857142857143, | |
| "o_win_rate": 0.014285714285714285, | |
| "draw_rate": 0.6714285714285714, | |
| "average_game_moves": 7.957142857142857, | |
| "policy_loss": 1.0146886479664357, | |
| "value_loss": 0.15539901554980812 | |
| }, | |
| { | |
| "iteration": 7, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.2571428571428571, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.7428571428571429, | |
| "average_game_moves": 8.085714285714285, | |
| "policy_loss": 0.8795330280319174, | |
| "value_loss": 0.11288299490796759 | |
| }, | |
| { | |
| "iteration": 8, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.24285714285714285, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.7571428571428571, | |
| "average_game_moves": 8.314285714285715, | |
| "policy_loss": 0.7982094690520712, | |
| "value_loss": 0.09204166978993948 | |
| }, | |
| { | |
| "iteration": 9, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.3, | |
| "o_win_rate": 0.014285714285714285, | |
| "draw_rate": 0.6857142857142857, | |
| "average_game_moves": 7.985714285714286, | |
| "policy_loss": 0.7609958442601752, | |
| "value_loss": 0.09048273768077822 | |
| }, | |
| { | |
| "iteration": 10, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.2857142857142857, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.7142857142857143, | |
| "average_game_moves": 8.17142857142857, | |
| "policy_loss": 0.7380844823857571, | |
| "value_loss": 0.08676699136799955 | |
| }, | |
| { | |
| "iteration": 11, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.18571428571428572, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.8142857142857143, | |
| "average_game_moves": 8.371428571428572, | |
| "policy_loss": 0.7269294456915653, | |
| "value_loss": 0.074583658938633 | |
| }, | |
| { | |
| "iteration": 12, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.3142857142857143, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.6857142857142857, | |
| "average_game_moves": 8.142857142857142, | |
| "policy_loss": 0.7146875767948779, | |
| "value_loss": 0.07327091548235175 | |
| }, | |
| { | |
| "iteration": 13, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.22857142857142856, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.7714285714285715, | |
| "average_game_moves": 8.17142857142857, | |
| "policy_loss": 0.7104355310823055, | |
| "value_loss": 0.07133727120433717 | |
| }, | |
| { | |
| "iteration": 14, | |
| "replay_examples": 24000, | |
| "x_win_rate": 0.2, | |
| "o_win_rate": 0.0, | |
| "draw_rate": 0.8, | |
| "average_game_moves": 8.371428571428572, | |
| "policy_loss": 0.7074488862714869, | |
| "value_loss": 0.06895742299867437 | |
| } | |
| ], | |
| "versus_random": { | |
| "games": 400, | |
| "wins": 384, | |
| "draws": 16, | |
| "losses": 0, | |
| "win_rate": 0.96, | |
| "non_loss_rate": 1.0, | |
| "average_moves": 6.065 | |
| }, | |
| "versus_exact_minimax": { | |
| "games": 200, | |
| "wins": 0, | |
| "draws": 200, | |
| "losses": 0, | |
| "win_rate": 0.0, | |
| "non_loss_rate": 1.0, | |
| "average_moves": 9.0 | |
| } | |
| } |