run:
  experiment_name: smoke
  max_iterations: 1
  seed: 1
  device: cpu

network:
  hidden_size: 16

traversal:
  traversals_per_player: 1
  max_depth: 2
  max_nodes_per_traversal: 64
  num_workers: 0
  worker_chunk_size: 1

optimization:
  advantage_batch_size: 2
  strategy_batch_size: 2
  advantage_updates_per_iteration: 1
  strategy_updates_per_iteration: 1
  learning_rate: 0.001

memory:
  advantage_capacity: 1000
  strategy_capacity: 1000

checkpoint:
  save_every: 0
  save_latest: false

evaluation:
  eval_every: 0
  games: 2
  opponents:
    - random
  max_steps: 10000