莫烦RL-01小例子

# Python 3.6.5 :: Anaconda, Inc.

import numpy as np
import pandas as pd
import time

np.random.seed(2)

N_STATUS = 5
ACTIONS = ['left', 'right']
EPSILON = 0.9
ALPHA = 0.1
LAMBDA = 0.9
MAX_EPISODES = 13
FRESH_TIME = 0.1

def build_q_table(n_status, actions):
    table = pd.DataFrame(
        np.zeros((n_status, len(actions))),
        columns=actions,
    )
    #print(table)
    return table

#build_q_table(5,[1])

def choose_action(state, q_table):
    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.argmax()
    return action_name

def get_env_feedback(S, A):
    if A == 'right':
        if S == N_STATUS - 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):
    env_list = ['-']*(N_STATUS-1)+['T']
    if S == 'terminal':
        interaction = 'Episode %d: total_steps = %s' % (episode+1, step_counter)
        print('
{}'.format(interaction), end='')
        time.sleep(1)
        print('
                               ', end='')
    else:
        env_list[S] = 'o'
        interaction = ''.join(env_list)
        print('
{}'.format(interaction), end='')
        time.sleep(FRESH_TIME)


def rl():
    q_table = build_q_table(N_STATUS, 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('
Q-table:
')
    print(q_table)