Add gates 1-2 audit and repair workflow

2026-07-05 17:55:22 +09:00
parent 94e9ac1854
commit fa9a1c5286
15 changed files with 1602 additions and 3 deletions
@@ -0,0 +1,40 @@
+run:
+  experiment_name: gates-1-2-replay-exploiter
+  seed: 20260705
+  learner_seat: 0
+  total_updates: 900
+  log_every: 10
+  checkpoint_every: 100
+  artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/exploiters
+
+opponent:
+  name: league_v1_update_500_frozen
+
+network:
+  hidden_size: 512
+  num_layers: 3
+
+ppo:
+  batch_games: 8192
+  rollout_steps: 400
+  gamma: 1.0
+  gae_lambda: 0.95
+  clip_epsilon: 0.2
+  entropy_coef: 0.01
+  value_coef: 0.5
+  max_grad_norm: 0.5
+  learning_rate: 0.0003
+  epochs: 4
+  minibatches: 128
+
+reward:
+  terminal_scale: 50.0
+  potential_shaping_initial: 0.0
+  potential_shaping_final: 0.0
+  potential_shaping_anneal_steps: 0
+
+evaluation:
+  games: 2000
+  duplicate: true
+  shuffle_bank_seed: 20260704
+  batch_games: 8192