171 datasets
2 datasets tagged "171"
Catan AI Self-Play Training Metrics (171 Iterations)
AlphaZero-style training run for Catan: policy/value losses, game lengths, MCTS agreement, and value calibration across 171 self-play iterations.
AlphaZero-Style Training Run: 171 Iterations of Self-Play
Policy and value network training metrics over 171 iterations, tracking loss convergence, game length, MCTS agreement, and value calibration.