#######################################################################
#?Copyright?（C）???????????????????????????????????????????????????????#
#?2016?-?2018?Shangtong?Zhang（zhangshangtong.cpp@gmail.com）???????????#
#?2016?Jan?Hakenberg（jan.hakenberg@gmail.com）?????????????????????????#
#?2016?Tian?Jun（tianjun.cpp@gmail.com）????????????????????????????????#
#?2016?Kenta?Shimada（hyperkentakun@gmail.com）?????????????????????????#
#?Permission?given?to?modify?the?code?as?long?as?you?keep?this????????#
#?declaration?at?the?top??????????????????????????????????????????????#
#######################################################################

import?numpy?as?np
import?pickle

BOARD_ROWS?=?3
BOARD_COLS?=?3
BOARD_SIZE?=?BOARD_ROWS?*?BOARD_COLS

class?State:
????def?__init__（self）:
????????#?the?board?is?represented?by?an?n?*?n?array
????????#?1?represents?a?chessman?of?the?player?who?moves?first
????????#?-1?represents?a?chessman?of?another?player
????????#?0?represents?an?empty?position
????????self.data?=?np.zeros（（BOARD_ROWS?BOARD_COLS））
????????self.winner?=?None
????????self.hash_val?=?None
????????self.end?=?None

????#?compute?the?hash?value?for?one?state?it‘s?unique
????def?hash（self）:
????????if?self.hash_val?is?None:
????????????self.hash_val?=?0
????????????for?i?in?self.data.reshape（BOARD_ROWS?*?BOARD_COLS）:
????????????????if?i?==?-1:
????????????????????i?=?2
????????????????self.hash_val?=?self.hash_val?*?3?+?i
????????return?int（self.hash_val）

????#?check?whether?a?player?has?won?the?game?or?it‘s?a?tie
????def?is_end（self）:
????????if?self.end?is?not?None:
????????????return?self.end
????????results?=?[]
????????#?check?row
????????for?i?in?range（0?BOARD_ROWS）:
????????????results.append（np.sum（self.data[i?:]））
????????#?check?columns
????????for?i?in?range（0?BOARD_COLS）:
????????????results.append（np.sum（self.data[:?i]））

????????#?check?diagonals
????????results.append（0）
????????for?i?in?range（0?BOARD_ROWS）:
????????????results[-1]?+=?self.data[i?i]
????????results.append（0）
????????for?i?in?range（0?BOARD_ROWS）:
????????????results[-1]?+=?self.data[i?BOARD_ROWS?-?1?-?i]

????????for?result?in?results:
????????????if?result?==?3:
????????????????self.winner?=?1
????????????????self.end?=?True
????????????????return?self.end
????????????if?result?==?-3:
????????????????self.winner?=?-1
????????????????self.end?=?True
????????????????return?self.end

????????#?whether?it‘s?a?tie
????????sum?=?np.sum（np.abs（self.data））
????????if?sum?==?BOARD_ROWS?*?BOARD_COLS:
????????????self.winner?=?0
????????????self.end?=?True
????????????return?self.end

????????#?game?is?still?going?on
????????self.end?=?False
????????return?self.end

????#?@symbol:?1?or?-1
????#?put?chessman?symbol?in?position?（i?j）
????def?next_state（self?i?j?symbol）:
????????new_state?=?State（）
????????new_state.data?=?np.copy（self.data）
????????new_state.data[i?j]?=?symbol
????????return?new_state

????#?print?the?board
????def?print_state（self）:
????????

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

????.......????????40??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\.gitignore

????.......???????148??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\.travis.yml

????.......?????11292??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter01\tic_tac_toe.py

????.......??????9151??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter02\ten_armed_testbed.py

????.......??????3808??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter03\grid_world.py

????.......??????7391??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter04\car_rental.py

????.......??????8716??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter04\car_rental_synchronous.py

????.......??????2445??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter04\gamblers_problem.py

????.......??????3436??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter04\grid_world.py

????.......?????13167??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter05\blackjack.py

????.......??????1814??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter05\infinite_variance.py

????.......??????9355??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter06\cliff_walking.py

????.......??????4269??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter06\maximization_bias.py

????.......??????6574??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter06\random_walk.py

????.......??????4018??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter06\windy_grid_world.py

????.......??????4249??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter07\random_walk.py

????.......??????1627??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter08\expectation_vs_sample.py

????.......?????23252??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter08\maze.py

????.......??????4892??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter08\trajectory_sampling.py

????.......?????15793??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter09\random_walk.py

????.......??????4262??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter09\square_wave.py

????.......??????9605??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter10\access_control.py

????.......?????13681??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter10\mountain_car.py

????.......?????11839??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter11\counterexample.py

????.......?????12140??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter12\mountain_car.py

????.......??????9679??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter12\random_walk.py

????.......??????8012??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\chapter13\short_corridor.py

????.......?????36003??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\images\example_13_1.png

????.......????238133??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\images\example_6_2.png

????.......?????31488??2019-03-14?04:56??《強化學習導論》第二版源代碼（python）\images\example_8_4.png

............此處省略67個文件信息