Q-Learnin算法实现
import numpy as np import pandas as pd import time np.random.seed(2) #environment N_STATES = 6 ACTIONS = ['left', 'right'] EPSILON = 0.9 ALPHA = 0.1 LAMBDA = 0.9 MAX_EPISODES = 13 FRESH_TIME = 0.01 def build_q_table(n_states, actions): table = pd.DataFrame( np.zeros((n_states, len(actions))), columns = actions, ) print(table) return table #build_q_table(N_STATES, ACTIONS) def choose_action(state, q_table): #This is how to choose an action state_actions = q_table.iloc[state, :] if(np.random.uniform() > EPSILON) or (state_actions.all() == 0): action_name = np.random.choice(ACTIONS) else: action_name = state_actions.idxmax() return action_name def get_env_feedback(S, A): #This is how agent will interact with the environment if A == 'right': #move right if S == N_STATES - 2: S = 'terminal' R = 1 else : S = S + 1 R = 0 else : R = 0 if S == 0: S = S else : S = S - 1 return S, R def update_env(S, episode, step_counter): # This is how environment be updated env_list = ['-']*(N_STATES - 1) + ['T'] if S == 'terminal': interaction = 'Episode %s: total_steps = %s' %(episode + 1, step_counter) print('\r{}'.format(interaction), end='') time.sleep(2) print('\r ', end='') else : env_list[S] = 'o' interaction = ''.join(env_list) print('\r{}'.format(interaction), end='') time.sleep(FRESH_TIME) def rl(): #main part of RL loop q_table = build_q_table(N_STATES, ACTIONS) for episode in range(MAX_EPISODES): step_counter = 0 S = 0 is_terminated = False update_env(S, episode, step_counter) while not is_terminated: A = choose_action(S, q_table) S_, R = get_env_feedback(S, A) q_predict = q_table.ix[S, A] if S_ != 'terminal': q_target = R + LAMBDA * q_table.iloc[S_, :].max() else: q_target = R is_terminated = True q_table.ix[S, A] += ALPHA * (q_target - q_predict) S = S_ update_env(S, episode, step_counter + 1) step_counter += 1 return q_table if __name__ == "__main__": q_table = rl() print('\r\n Q-table: \n') print(q_table)
