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

pseudocode.py

# At the end of a simulation, we propagate the evaluation all the way up the
# tree to the root.
def backpropagate(search_path: List[Node], value: float, to_play: Player,
                  discount: float, min_max_stats: MinMaxStats):
  for node in search_path:
    node.value_sum += value if node.to_play == to_play else -value
    node.visit_count += 1
    min_max_stats.update(node.value())

    value = node.reward + discount * value