deep_learning_and_the_game_of_go

deep_learning_and_the_game_of_go copied to clipboard

chapter 8: Cannot receive GTP response from bot

6

On windows, self.gtp_stream.stdout.readline() will loop infinitely when an empty line is returned by the bot (e.g. gnugo).

Sarah112358

Chapter 13: Possible errors in AlphaGoMCTS agent

4

1. In dlgo.agent.alphago.AlphaGoMCTS we have the policy rollout function in line 142. ``` def policy_rollout(self, game_state): for step in range(self.rollout_limit): if game_state.is_over(): break move_probabilities = self.rollout_policy.predict(game_state) encoder = self.rollout_policy.encoder valid_moves...

JingOY0610

chapter 13: alphago_policy_sl.py

8

I would like to report a result of excuting alphago_policy_sl.py(ch.13). Hope, to know the reason why I got the error message from the original python script. modify[1]:necessary for windows10 using...

yoshih-2go

(base) C:\Users\Lenovo\PycharmProjects\Python-go>python generated_mcts_game.py ­-n 20 ­­--board­out features.npy ­­--move­-out labels.npy usage: generated_mcts_game.py [-h] [--board-size BOARD_SIZE] [--rounds ROUNDS] [--temperature TEMPERATURE] [--max-moves MAX_MOVES] [--num-games NUM_GAMES] [--board-out BOARD_OUT] [--move-out MOVE_OUT] generated_mcts_game.py: error: unrecognized arguments:...

computer-idol

Chapter 4 crashes when entering a coordinate while player against mcts

1

`python mcts_go.py` and entering the first coordinate results in: ``` Traceback (most recent call last): File "mcts_go.py", line 47, in main() File "mcts_go.py", line 41, in main move = bot.select_move(game)...

olbrichj

How to compute the winner? would you please explain the implementation in the scoring.py?

3

computer-idol

пункт 3.4. bot_v_bot.py

1

puteets66066

ValueError on end_to_end.py Chapter 8.2.1

2

I am getting an error running the end_to_end.py from github: ``` KGS-2003-19-7582-.tar.gz 7582 KGS-2002-19-3646-.tar.gz 3646 KGS-2001-19-2298-.tar.gz 2298 total num games: 179689 Drawn 100 samples: Traceback (most recent call last): File...

Tuxius

Why create a new Node as Root at this position?

1

https://github.com/maxpumperla/deep_learning_and_the_game_of_go/blob/c1add1ff272f8927a82d81c9ee430f9c13e062ef/code/dlgo/agent/alphago.py#L118 Hi Max, hi Kevin, What is the point of a) Creating a new Root node here and then also b) testing if the move is in root.children? We have...

artus-LYTiQ

https://github.com/maxpumperla/deep_learning_and_the_game_of_go/blob/c1add1ff272f8927a82d81c9ee430f9c13e062ef/code/dlgo/agent/alphago.py#L153 Heyho, where am I mistaken here: to me it looks like if the `greedy_move` is not legal, this loop will then simply try to select the same move (unsuccessfully)...

artus-LYTiQ