├── .gitignore ├── Alpha Toe.pdf ├── LICENSE ├── README.md ├── common ├── __init__.py ├── base_game_spec.py ├── benchmark.py └── network_helpers.py ├── connect_4 ├── __init__.py ├── network.py ├── position_connect_4_min_max_depth_6 ├── supervised.py ├── train_historical.py └── train_vs_min_max.py ├── games ├── __init__.py ├── connect_4.py ├── tic_tac_toe.py └── tic_tac_toe_x.py ├── policy_gradient.py ├── policy_gradient_historical_competition.py ├── requirements.txt ├── techniques ├── __init__.py ├── create_positions_set.py ├── min_max.py ├── monte_carlo.py ├── monte_carlo_uct_with_value.py ├── train_policy_gradient.py ├── train_policy_gradient_historic.py ├── train_supervised.py └── train_value_network.py ├── tests ├── __init__.py ├── common │ ├── __init__.py │ └── test_network_helpers.py ├── games │ ├── __init__.py │ ├── test_connect_4.py │ └── test_tic_tac_toe_x.py └── techniques │ ├── __init__.py │ ├── test_create_positions_set.py │ ├── test_min_max.py │ ├── test_train_policy_gradient.py │ └── test_train_policy_gradient_historic.py ├── tic_tac_toe_5_4 ├── __init__.py ├── network.py ├── position_tic_tac_toe_5_4_min_max_depth_6 ├── supervised.py ├── train_historical.py └── train_vs_min_max.py └── value_network.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/.gitignore -------------------------------------------------------------------------------- /Alpha Toe.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/Alpha Toe.pdf -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/README.md -------------------------------------------------------------------------------- /common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /common/base_game_spec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/common/base_game_spec.py -------------------------------------------------------------------------------- /common/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/common/benchmark.py -------------------------------------------------------------------------------- /common/network_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/common/network_helpers.py -------------------------------------------------------------------------------- /connect_4/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /connect_4/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/connect_4/network.py -------------------------------------------------------------------------------- /connect_4/position_connect_4_min_max_depth_6: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/connect_4/position_connect_4_min_max_depth_6 -------------------------------------------------------------------------------- /connect_4/supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/connect_4/supervised.py -------------------------------------------------------------------------------- /connect_4/train_historical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/connect_4/train_historical.py -------------------------------------------------------------------------------- /connect_4/train_vs_min_max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/connect_4/train_vs_min_max.py -------------------------------------------------------------------------------- /games/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /games/connect_4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/games/connect_4.py -------------------------------------------------------------------------------- /games/tic_tac_toe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/games/tic_tac_toe.py -------------------------------------------------------------------------------- /games/tic_tac_toe_x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/games/tic_tac_toe_x.py -------------------------------------------------------------------------------- /policy_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/policy_gradient.py -------------------------------------------------------------------------------- /policy_gradient_historical_competition.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/policy_gradient_historical_competition.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow=0.7.1 2 | -------------------------------------------------------------------------------- /techniques/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /techniques/create_positions_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/create_positions_set.py -------------------------------------------------------------------------------- /techniques/min_max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/min_max.py -------------------------------------------------------------------------------- /techniques/monte_carlo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/monte_carlo.py -------------------------------------------------------------------------------- /techniques/monte_carlo_uct_with_value.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/monte_carlo_uct_with_value.py -------------------------------------------------------------------------------- /techniques/train_policy_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/train_policy_gradient.py -------------------------------------------------------------------------------- /techniques/train_policy_gradient_historic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/train_policy_gradient_historic.py -------------------------------------------------------------------------------- /techniques/train_supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/train_supervised.py -------------------------------------------------------------------------------- /techniques/train_value_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/techniques/train_value_network.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/common/test_network_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tests/common/test_network_helpers.py -------------------------------------------------------------------------------- /tests/games/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/games/test_connect_4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tests/games/test_connect_4.py -------------------------------------------------------------------------------- /tests/games/test_tic_tac_toe_x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tests/games/test_tic_tac_toe_x.py -------------------------------------------------------------------------------- /tests/techniques/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/techniques/test_create_positions_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tests/techniques/test_create_positions_set.py -------------------------------------------------------------------------------- /tests/techniques/test_min_max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tests/techniques/test_min_max.py -------------------------------------------------------------------------------- /tests/techniques/test_train_policy_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tests/techniques/test_train_policy_gradient.py -------------------------------------------------------------------------------- /tests/techniques/test_train_policy_gradient_historic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tests/techniques/test_train_policy_gradient_historic.py -------------------------------------------------------------------------------- /tic_tac_toe_5_4/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tic_tac_toe_5_4/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tic_tac_toe_5_4/network.py -------------------------------------------------------------------------------- /tic_tac_toe_5_4/position_tic_tac_toe_5_4_min_max_depth_6: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tic_tac_toe_5_4/position_tic_tac_toe_5_4_min_max_depth_6 -------------------------------------------------------------------------------- /tic_tac_toe_5_4/supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tic_tac_toe_5_4/supervised.py -------------------------------------------------------------------------------- /tic_tac_toe_5_4/train_historical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tic_tac_toe_5_4/train_historical.py -------------------------------------------------------------------------------- /tic_tac_toe_5_4/train_vs_min_max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/tic_tac_toe_5_4/train_vs_min_max.py -------------------------------------------------------------------------------- /value_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DanielSlater/AlphaToe/HEAD/value_network.py --------------------------------------------------------------------------------