run:
  experiment_name: jax-ppo-smoke
  seed: 20260704
  learner_seat: 0
  total_updates: 1
  log_every: 1
  checkpoint_every: 1
  artifact_root: runs/tmp/jax-ppo-artifacts

opponent:
  name: discard_only

network:
  hidden_size: 64
  num_layers: 2

ppo:
  batch_games: 64
  rollout_steps: 64
  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: 1
  minibatches: 4

reward:
  terminal_scale: 50.0
  potential_shaping_initial: 1.0
  potential_shaping_final: 0.0
  potential_shaping_anneal_steps: 100000

evaluation:
  games: 128
  duplicate: true
  shuffle_bank_seed: 20260704
  batch_games: 64