OpenAI-Gym and Keras-RL: DQN expects a model that has one dimension for each action

Question

I am trying to set a Deep-Q-Learning agent with a custom environment in OpenAI Gym. I have 4 continuous state variables with individual limits and 3 integer action variables with individual limits.

Here is the code:

#%% import 
from gym import Env
from gym.spaces import Discrete, Box, Tuple
import numpy as np


#%%
class Custom_Env(Env):

    def __init__(self):
        
       # Define the state space
       
       #State variables
       self.state_1 = 0
       self.state_2 =  0
       self.state_3 = 0
       self.state_4_currentTimeSlots = 0
       
       #Define the gym components
       self.action_space = Box(low=np.array([0, 0, 0]), high=np.array([10, 20, 27]), dtype=np.int)    
                                                                             
       self.observation_space = Box(low=np.array([20, -20, 0, 0]), high=np.array([22, 250, 100, 287]),dtype=np.float16)

    def step(self, action ):

        # Update state variables
        self.state_1 = self.state_1 + action [0]
        self.state_2 = self.state_2 + action [1]
        self.state_3 = self.state_3 + action [2]

        #Calculate reward
        reward = self.state_1 + self.state_2 + self.state_3
       
        #Set placeholder for info
        info = {}    
        
        #Check if it's the end of the day
        if self.state_4_currentTimeSlots >= 287:
            done = True
        if self.state_4_currentTimeSlots < 287:
            done = False       
        
        #Move to the next timeslot 
        self.state_4_currentTimeSlots +=1

        state = np.array([self.state_1,self.state_2, self.state_3, self.state_4_currentTimeSlots ])

        #Return step information
        return state, reward, done, info
        
    def render (self):
        pass
    
    def reset (self):
       self.state_1 = 0
       self.state_2 =  0
       self.state_3 = 0
       self.state_4_currentTimeSlots = 0
       state = np.array([self.state_1,self.state_2, self.state_3, self.state_4_currentTimeSlots ])
       return state

#%% Set up the environment
env = Custom_Env()

#%% Create a deep learning model with keras


from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.optimizers import Adam

def build_model(states, actions):
    model = Sequential()
    model.add(Dense(24, activation='relu', input_shape=states))
    model.add(Dense(24, activation='relu'))
    model.add(Dense(actions[0] , activation='linear'))
    return model

states = env.observation_space.shape 
actions = env.action_space.shape 
print("env.observation_space: ", env.observation_space)
print("env.observation_space.shape : ", env.observation_space.shape )
print("action_space: ", env.action_space)
print("action_space.shape : ", env.action_space.shape )


model = build_model(states, actions)
print(model.summary())

#%% Build Agent wit Keras-RL
from rl.agents import DQNAgent
from rl.policy import BoltzmannQPolicy
from rl.memory import SequentialMemory

def build_agent (model, actions):
    policy = BoltzmannQPolicy()
    memory = SequentialMemory(limit = 50000, window_length=1)
    dqn = DQNAgent (model = model, memory = memory, policy=policy,
                    nb_actions=actions, nb_steps_warmup=10, target_model_update= 1e-2)
    return dqn

dqn = build_agent(model, actions)
dqn.compile(Adam(lr=1e-3), metrics = ['mae'])
dqn.fit (env, nb_steps = 4000, visualize=False, verbose = 1)

When I run this code I get the following error message

ValueError: Model output "Tensor("dense_23/BiasAdd:0", shape=(None, 3), dtype=float32)" has invalid shape. DQN expects a model that has one dimension for each action, in this case (3,).

thrown by the line dqn = DQNAgent (model = model, memory = memory, policy=policy, nb_actions=actions, nb_steps_warmup=10, target_model_update= 1e-2)

Can anyone tell me, why this problem is occuring and how to solve this issue? I assume it has something to do with the built model and thus with the action and state spaces. But I could not figure out what exactly the problem is.

Reminder on the bounty: My bounty is expiring quite soon and unfortunately, I still have not received any answer. If you at least have a guess how to tackle that problem, I'll highly appreciate if you share your thoughts with me and I would be quite thankful for it.

Answer 1

Adding a flatten layer before the final output can solve this error. Example:

def build_model(states, actions):
    model = Sequential()
    model.add(Dense(24, activation='relu', input_shape=states))
    model.add(Dense(24, activation='relu'))
    model.add(Flatten())
    model.add(Dense(actions[0] , activation='linear'))
    return model