flappy_double_dqn.py 文件源码

def run_pretrained(input_state,model,action_states,gameState):
    print '\n\nLoading pretrained weights onto model...'

    model.load_weights(p.PRETRAINED_PATH)
    epsilon=1
    while True:
        print 'Running pretrained model (no exploration) with weights at ', p.PRETRAINED_PATH 

        nn_out = model.predict(input_state,batch_size=1,verbose=0)
        nn_action = [[0,0]]
        nn_action[0][np.argmax(nn_out)] =1
        action,rand_flag = select_action(nn_action+action_states,prob=[epsilon,(1-epsilon)*1/7,(1-epsilon)*6/7])
        rgbDisplay, reward, tState = gameState.frame_step(action)
        grayDisplay = (np.dot(np.fliplr(imrotate(imresize(rgbDisplay, (80,80), interp='bilinear'), -90))[:,:,:3], [0.299, 0.587, 0.114])).reshape((1,1,80,80))
        output_state = np.append(grayDisplay,input_state[:,:p.HISTORY-1,:,:], axis=1)


#############################################################################################################################################################################