BlackRobot_SARSA_Trace.py 文件源码

def choose_action(d, c, q_table):

    global epsilon
    state_actions = q_table[d][c][:]

    # random move or no data recorded for this state yet
    if (np.random.uniform() < epsilon) or (np.sum(state_actions) == 0):

        action_chose = np.random.randint(n_actions)

        # decrease random moves over time to a minimum of 10%
        if epsilon >  0.1: epsilon *= 0.9

    else:
        action_chose = state_actions.argmax()

    return action_chose