select_action (https://arxiv.org/src/1911.08265v1/anc/pseudocode.py)

pseudocode.py

def select_action(config: MuZeroConfig, num_moves: int, node: Node,
                  network: Network):
  visit_counts = [
      (child.visit_count, action) for action, child in node.children.items()
  ]
  t = config.visit_softmax_temperature_fn(
      num_moves=num_moves, training_steps=network.training_steps())
  _, action = softmax_sample(visit_counts, t)
  return action

def visit_softmax_temperature(num_moves, training_steps):
  if num_moves < 30:
    return 1.0
  else:
    return 0.0  # Play according to the max.