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

pseudocode.py

# We expand a node using the value, reward and policy prediction obtained from
# the neural network.
def expand_node(node: Node, to_play: Player, actions: List[Action],
                network_output: NetworkOutput):
  node.to_play = to_play
  node.hidden_state = network_output.hidden_state
  node.reward = network_output.reward
  policy = {a: math.exp(network_output.policy_logits[a]) for a in actions}
  policy_sum = sum(policy.values())
  for action, p in policy.items():
    node.children[action] = Node(p / policy_sum)