keras-rl is a Reinforcement Learning library based on Keras
The code can be found at github.com/matthiasplappert/keras-rl.
Questions tagged [keras-rl]
81 questions
0
votes
1 answer
Keras-RL2 and Tensorflow 1-2 Incompatibility
I am getting;
tensorflow.python.framework.errors_impl.OperatorNotAllowedInGraphError: Using a symbolic `tf.Tensor` as a Python `bool` is not allowed in Graph execution. Use Eager execution or decorate this function with @tf.function.
Error while…
user10767584
0
votes
0 answers
to_categorical function in KerasR not working
I am using the to_categorical function in KerasR and it throws an error message in RStudio which is this:
mnist_y <- to_categorical(mnist_y, 10)
Collecting package metadata (current_repodata.json): ...working... failed
CondaSSLError: OpenSSL appears…
gerluc
- 25
- 4
0
votes
0 answers
Continuous action space with discreate steps
How can I make a custom environment with a continues action space but with a specific step. For example:
self.action_space = Box(low=np.array([0,0,0]), high=np.array([+1,+1,+1]), dtype=np.float32)
gives a continues action space with 3 actions. So…
0
votes
0 answers
Cannot compile DQN agent: TypeError: ('Keyword argument not understood:', 'units')
I have this model:
poss_in = layers.Input((1,))
poss_lr = layers.Dense(8, activation='relu')(poss_in)
hist_in = layers.Input((100,))
hist_lr = layers.Reshape((100, 1))(hist_in)
hist_lr = layers.LSTM(32)(hist_lr)
hist_lr = layers.Dense(32,…
Ok-src
- 1
- 2
0
votes
1 answer
Keras-rl ValueError"Model has more than one output. DQN expects a model that has a single output"
Is there any way to get around this error? I have a model with a 15x15 input grid, which leads to two outputs. Each output has 15 possible values, which are x or y coordinates. I did this because it is significantly simpler than having 225 separate…
Mercury
- 298
- 1
- 11
0
votes
1 answer
real tme keras rl DQN predictions
hello everyone I followed that tutorial
https://www.youtube.com/watch?v=hCeJeq8U0lo&list=PLgNJO2hghbmjlE6cuKMws2ejC54BTAaWV&index=2
to train a DQN Agent
everything works
env = gym.make('CartPole-v0')
states = env.observation_space.shape[0]
actions =…
abdelmoumen
- 33
- 4
0
votes
0 answers
ValueError: Input 0 of layer Conv2D_1 is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: [None, 3, 210, 160, 3]
I want to build a CNN model that takes 3 successive images insetead of one, so the input takes the shape: (3,height, width, channels=3) :
from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Dropout, Dense,
Flatten,Convolution2D
from…
Housseyne NADOUR
- 1
- 1
0
votes
1 answer
How to use a trained RL model to make a prediction?
I would like to use my trained RL model for a discrete test prediction.
This is how the model is built:
model = Sequential()
model.add(Dense(60, activation='relu', input_shape=states))
model.add(Dense(60, activation='relu',…
Vincent Roye
- 2,751
- 7
- 33
- 53
0
votes
1 answer
Dueling DQN updates model architecture and causes issues
I create an initial network model with the following acrchitecture.
def create_model(env):
dropout_prob = 0.8 #aggresive dropout regularization
num_units = 256 #number of neurons in the hidden units
model = Sequential()
…
0
votes
1 answer
How to install keras-rl in Anaconda
I am starting to work on a reinforcement learning model, but I am blocked at the moment as I have not been able to download one of the essential python packages yet: keras-rl.
More specifically, I would like to import the following 3 utilities:
from…
el_pazzu
- 81
- 3
- 12
0
votes
3 answers
Keras LSTM layers in Keras-rl
I am trying to implement a DQN agent using Keras-rl. The problem is that when I define my model I need to use an LSTM layer in the architecture:
model = Sequential()
model.add(Flatten(input_shape=(1, 8000)))
model.add(Reshape(target_shape=(200,…
Anto
- 119
- 1
- 13
0
votes
2 answers
Cant import keras-rl in jupyter notebooks
I have been trying to import kera-rl into my jupyter notebook but i get this error every time i try.
ModuleNotFoundError: No module named 'rl'
How do I stop getting this error?
bugsiesegal
- 21
- 6
0
votes
0 answers
Memory error when using keras-rl for reinforcement learning
I use the keras-rl and run the eample of keras-rl, namely, dqn_cartpole.py successfully.
Then I change the env_name to play the Pong game, i.e., env_name = "PongNoFrameskip-v4".
All thing looks good, however, the program break suddenly with Memory…
LinTIna
- 481
- 1
- 6
- 14
0
votes
1 answer
Deep Reinforcement Learning (keras-rl) Early stopping
According to these guys (https://nihit.github.io/resources/spaceinvaders.pdf) it is possible to perform Early Stopping with Deep Reinforcement Learning. I used that before with Deep Learning on Keras, but, how to do that on keras-rl? in the same…
mad
- 2,677
- 8
- 35
- 78
0
votes
2 answers
Deep Reinforcement Learning Training Accuracy
I am using a deep reinforcement learning approach to predict time series behavior. I am quite a newbie on that so my question is more conceptual than a computer programming one. My colleague has given me the following chart, with training,…
mad
- 2,677
- 8
- 35
- 78