I’m trying to make a Flappy Bird AI, using the flappy_bird_gym repository using Tensorflow. I have created an environment using conda in WSL2, tensorflow version 2.17, with keras-rl2 and keras 3, python 3.10.14.

But when I try to build my DQN error I get this error.

Here’s the code snippet,

import flappy_bird_gym
env = flappy_bird_gym.make("FlappyBird-v0")

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

from rl.agents import DQNAgent
from rl.memory import SequentialMemory
from rl.policy import LinearAnnealedPolicy, EpsGreedyQPolicy

def build_model(input, actions):
    model = Sequential()
    model.add(Flatten(input_shape=(1, input)))
    model.add(Dense(64, activation='relu'))
    model.add(Dense(128, activation='relu'))
    model.add(Dense(256, activation='relu'))
    model.add(Dense(64, activation='relu'))
    model.add(Dense(128, activation='relu'))
    model.add(Flatten(input_shape=(1, input)))

    model.add(Dense(actions, activation='linear'))
    model.summary()
    return model

obs = env.observation_space.shape[0]
actions = env.action_space.n

model = build_model(obs, actions)

Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ flatten (Flatten)               │ (None, 2)              │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 64)             │           192 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_1 (Dense)                 │ (None, 128)            │         8,320 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_2 (Dense)                 │ (None, 256)            │        33,024 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_3 (Dense)                 │ (None, 64)             │        16,448 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_4 (Dense)                 │ (None, 128)            │         8,320 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ flatten_1 (Flatten)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_5 (Dense)                 │ (None, 2)              │           258 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 66,562 (260.01 KB)
 Trainable params: 66,562 (260.01 KB)
 Non-trainable params: 0 (0.00 B)

def build_agent(model, actions):
    policy = LinearAnnealedPolicy(EpsGreedyQPolicy(), attr='eps', value_max=0.5, value_min=.0001, value_test=.0, nb_steps=6000000)
    memory = SequentialMemory(limit=100000, window_length=1)
    dqn = DQNAgent(model=model, memory=memory, policy=policy,
                enable_dueling_network=True, dueling_type='avg',
                nb_actions=actions, nb_steps_warmup=500)
    return dqn
model.compile(optimizer=Adam(learning_rate=0.0025), loss='mse')
dqn = build_agent(model, actions)

**Error: **

ValueError                                Traceback (most recent call last)
Cell In[7], line 9
      7     return dqn
      8 model.compile(optimizer=Adam(learning_rate=0.0025), loss='mse')
----> 9 dqn = build_agent(model, actions)

Cell In[7], line 4, in build_agent(model, actions)
      2 policy = LinearAnnealedPolicy(EpsGreedyQPolicy(), attr='eps', value_max=0.5, value_min=.0001, value_test=.0, nb_steps=6000000)
      3 memory = SequentialMemory(limit=100000, window_length=1)
----> 4 dqn = DQNAgent(model=model, memory=memory, policy=policy,
      5             enable_dueling_network=True, dueling_type='avg',
      6             nb_actions=actions, nb_steps_warmup=500)
      7 return dqn

File ~/miniconda3/envs/env/lib/python3.10/site-packages/rl/agents/dqn.py:106, in DQNAgent.__init__(self, model, policy, test_policy, enable_double_dqn, enable_dueling_network, dueling_type, *args, **kwargs)
    103 super().__init__(*args, **kwargs)
    105 # Validate (important) input.
--> 106 if list(model.output.shape) != list((None, self.nb_actions)):
    107     raise ValueError(f'Model output "{model.output}" has invalid shape. DQN expects a model that has one dimension for each action, in this case {self.nb_actions}.')
    109 # Parameters.

File ~/miniconda3/envs/env/lib/python3.10/site-packages/keras/src/ops/operation.py:266, in Operation.output(self)
    256 @property
    257 def output(self):
    258     """Retrieves the output tensor(s) of a layer.
    259 
    260     Only returns the tensor(s) corresponding to the *first time*
   (...)
    264         Output tensor or list of output tensors.
    265     """
--> 266     return self._get_node_attribute_at_index(0, "output_tensors", "output")

File ~/miniconda3/envs/env/lib/python3.10/site-packages/keras/src/ops/operation.py:285, in Operation._get_node_attribute_at_index(self, node_index, attr, attr_name)
    269 """Private utility to retrieves an attribute (e.g. inputs) from a node.
    270 
    271 This is used to implement the properties:
   (...)
    282     The operation's attribute `attr` at the node of index `node_index`.
    283 """
    284 if not self._inbound_nodes:
--> 285     raise ValueError(
    286         f"The layer {self.name} has never been called "
    287         f"and thus has no defined {attr_name}."
    288     )
    289 if not len(self._inbound_nodes) > node_index:
    290     raise ValueError(
    291         f"Asked to get {attr_name} at node "
    292         f"{node_index}, but the operation has only "
    293         f"{len(self._inbound_nodes)} inbound nodes."
    294     )

ValueError: The layer sequential has never been called and thus has no defined output.