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
0 answers
Could I use tf.session() in enviroment where keras only used?
Thanks for reading my question.
I was using keras to develop my reinforcement learning agent based on keres-rl. But I want to upgrade my agent so that I get some update from open ai base line code for better action exploration. But the code used…
verystrongjoe
- 3,831
- 9
- 35
- 66
0
votes
2 answers
Where Can I find the implemented DQfDAgent?
I'm trying to use that Object as This Blog uses in His Code but when I do from rl.agents.dqn import DQfDAgent it returns me and error ImportError: cannot import name 'DQfDAgent'.
I've done a dir(rl.agents.dqn) and there is no DQfDAgent object so,…
Angelo
- 575
- 3
- 18
0
votes
0 answers
Reinforcement learning: why does the accuracy of the learning drops after restarting the training?
I have developed a small reinforcement learning exercise. The problem is that the accuracy of the training drops enormously after restarting the training which I don't really understand.
The environment:
- I use keras rl, a simple neuronal model,…
pittnerf
- 739
- 1
- 6
- 17
0
votes
1 answer
How to call LSTM function?
I am just getting started with LSTM time series forecasting example.
Getting a below error at the last step, not sure what am i missing here.
Any help would be greatly appreciated!.ERROR- NameError: name 'to_list' is not defined
def…
RSingh
- 51
- 1
- 6
0
votes
0 answers
Scale actor network output to the action space bounds in Keras Rl
I am trying to implement DDPG from Keras RL and have the following actor network.
actor = Sequential()
actor.add(Flatten(input_shape=(1,) +…
CS101
- 444
- 1
- 6
- 21
0
votes
1 answer
Keras-RL episodes returning same values after fitting model
So I have created a custom environment using OpenAI Gym. I'm closely following the keras-rl examples of the DQNAgent for the CartPole example which leads to the following implementation:
nb_actions = env.action_space.n
# Option 1 : Simple…
user3745453
- 1
- 1