Initial Transitions for Q-Learning Agent is empty

[Skorkmaz88]

When I run the AI.py, initial transition data is (None, None) which is causing a crush

`---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
in ()
1 from Board import *
----> 2 from AI import *

/home/semih/ozu/rl/homework1/Checkers-Reinforcement-Learning/AI.py in ()
554 validation_info = []
555 for j in range(NUM_TRAINING_ROUNDS):
--> 556 training_info.extend(play_n_games(PLAYER1, PLAYER2, NUM_GAMES_TO_TRAIN, TRAINING_MOVE_LIMIT))
557 PLAYER1.print_transition_information(PLAYER1.get_transitions_information())
558 PLAYER1.set_random_move_probability(0)

/home/semih/ozu/rl/homework1/Checkers-Reinforcement-Learning/AI.py in play_n_games(player1, player2, num_games, move_limit)
457 outcome_counter[j][5] = piece_counter[3]
458
--> 459 player1.game_completed()
460 player2.game_completed()
461 #game_board.print_board()

/home/semih/ozu/rl/homework1/Checkers-Reinforcement-Learning/AI.py in game_completed(self)
169 transition = (self.pre_last_move_state ,self.post_last_move_state)
170
--> 171 self.transitions[transition] = self.transitions[transition] + self.learning_rate * reward_function(transition[0],cur_state)
172
173 self.pre_last_move_state = None

KeyError: (None, None).`