Issue while solving Gym Environment ; ValueError: Weights for model sequential have not yet been created - tf.keras

Question

I am new to stackoverflow, so I apologize for any errors while asking a question. I am trying to solve the cartpole-v1 gym environment using a dqn agent. I am facing an issue as follows ValueError: Weights for model sequential have not yet been created. Weights are created when the Model is first called on inputs or build() is called with an input_shape. I've searched how to fix this but to no success. My tensorflow version is 2.8.0. My code for my agent is as follows. I believe, the problem is most probably due to my build_model and in the model.fit line. This is the error that I am facing
class DQNAgent0:
def __init__(self, state_size, action_size):
self.state_size = state_size
self.action_size = action_size
self.memory = deque(maxlen=2000)
self.gamma = 0.95 # discount factor
self.epsilon = 1.0 # 100% exploration at the start
self.epsilon_decay = 0.995
self.epsilon_min = 0.01
self.learning_rate = 0.001
self.model = self._build_model()
def _build_model(self):
'''model = tf.keras.Sequential([
tf.keras.layers.Dense(1),
#tf.keras.Input((self.state_size,)),
tf.keras.layers.Dense(24, activation="relu"),
tf.keras.layers.Dense(24, activation="relu"),
tf.keras.layers.Dense(self.action_size, activation="linear"),
])
model.compile(loss=tf.keras.losses.mse,
optimizer=tf.keras.optimizers.Adam(learning_rate=self.learning_rate))'''
#model = tf.keras.Sequential()
model = tf.keras.Sequential([tf.keras.layers.Dense(1)])
model.add(tf.keras.Input(shape = self.state_size))
model.add(tf.keras.layers.Dense(24, activation = 'relu'))
model.add(tf.keras.layers.Dense(24, activation = 'relu'))
model.add(tf.keras.layers.Dense(self.action_size, activation = 'linear'))
#opt = tf.keras.optimizers.Adam(learning_rate = self.learning_rate)
#model.compile(loss = 'mse', optimizer = opt)
model.compile(loss = tf.keras.losses.mse, optimizer = tf.keras.optimizers.Adam(learning_rate = self.learning_rate))
return model
def remember(self, state, action, reward, next_state, done):
self.memory.append((state, action, reward, next_state, done))
def act(self, state):
if np.random.rand() <= self.epsilon:
return random .randrange(self.action_size) # exploratory action
act_values = self.model.predict(state)
return np.argmax(act_values[0])
def replay(self, batch_size):
#creating a random sample from our memory
minibatch = random.sample(self.memory, batch_size)
for state, action, reward, next_state, done in minibatch:
target = reward
if not done:
target = (reward + self.gamma * np.amax(self.model.predict(next_state[0]))) # reward at current timestep + discounted future reward
target_f = self.model.predict(state)
target_f[0][action] = target #mapping future reward to the current reward
self.model.fit(tf.expand_dims(state, axis=-1), target_f, epochs = 1, verbose = 0) # fitting a model to train with state as input x and target_f as y (predicted future reward)
if self.epsilon > self.epsilon_min:
self.epsilon *= self.epsilon_decay
def load(self, name):
self.model.load_weights(name)
def save(self, name):
self.model.save_weights(name)