Skip to content

"We record the state and the probabilities produced by the MCTS." - do you mean board state, priors and values? #11

Description

@shanemcandrewai

In your blog, you emphasize "We record the state and the probabilities produced by the MCTS" Do you mean we record board state, priors and values? Trainer.exceute_episode ret.append((hist_state, hist_action_probs, reward * ((-1) ** (hist_current_player != current_player))))

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions