Stack Overflow
Stack Overflow

Questions tagged [dqn]

DQN is a multi-layered neural network, added target network and experience replay to Q-learning

206 questions
16
votes
7 answers

PyTorch Model Training: RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR

After training a PyTorch model on a GPU for several hours, the program fails with the error RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR Training Conditions Neural Network: PyTorch 4-layer nn.LSTM with nn.Linear output Deep Q Network…
Athena Wisdom
  • 6,101
  • 9
  • 36
  • 60
4
votes
0 answers

How to extract weights of DQN agent in TF-Agents framework?

I am using TF-Agents for a custom reinforcement learning problem, where I train a DQN (constructed using DqnAgents from the TF-Agents framework) on some features from my custom environment, and separately use a keras convolutional model to extract…
Tarun Sriram
  • 41
  • 1
4
votes
0 answers

how to get the dimension of Openai gym spaces.Tuple to be used in DQN when building neural network with Keras

I built a cumstom environment with Openai Gym spaces.Tuple because my observation is made up of: hour(0-23), day(1-7), month(1-12), which are discrete; four continuous numbers, which are from a csv file; and an array of shape (4*24), which are also…
Yuchen
  • 81
  • 5
4
votes
1 answer

How to continue the DQN or DDPG training after previous training is interrupted? D

When doing reinforcement learning, I have to start training from the beginning each time. It costs lots of time. Is there any solution on starting training from the previous training results? Thanks.
seabiscuit
  • 41
  • 1
3
votes
0 answers

updating a DQN in R using neuralnet

I am trying to implement a simple case of deep Q learning in R, using the neuralnet package. I have an initial network with initial random weights. I use it to generate some experience for my agent and as a result, I get states and targets. Then I…
Andreas
  • 31
  • 1
3
votes
1 answer

How to build a DQN that outputs 1 discrete and 1 continuous value as a pair?

I am building a DQN for an Open Gym environment. My observation space is only 1 discrete value but my actions are: self.action_space = (Discrete(3), Box(-100, 100, (1,))) ex: [1,56], [0,24], [2,-78]... My current neural network is: model =…
Vincent Roye
  • 2,751
  • 7
  • 33
  • 53
3
votes
1 answer

Understanding and Evaluating different methods in Reinforcement Learning

I have been trying to implement the Reinforcement learning algorithm on Python using different variants like Q-learning, Deep Q-Network, Double DQN and Dueling Double DQN. Consider a cart-pole example and to evaluate the performance of each of these…
mkpisk
  • 152
  • 1
  • 9
3
votes
0 answers

assert observation is not None AssertionError when creating observation space for custom environment

EDIT: Fixed it eventually. Solution in bottom of question I want to create a custom environment to play a game. It plays by using a screengrab of the game as an input and using a DQN outputs either jump, or don't. I have tried a few ways of creating…
Otto Hodne-Tandberg
  • 31
  • 3
3
votes
3 answers

Tensorflow 2.0 DQN Agent Issue with Custom Environment

So I've been following the DQN agent example / tutorial and I set it up like in the example, only difference is that I built my own custom python environment which I then wrapped in TensorFlow. However, no matter how I shape my observations and…
Ibraheem Nofal
  • 487
  • 1
  • 6
  • 13
2
votes
1 answer

Why is my DQN-agent's training so inefficient?

I am trying to train an agent to play tic-tac-toe perfectly as a second player (the first player walks randomly) with the DQN-agent from tf-agents, but my training is extremely slow. For 100_000 steps, the model did not improve its results in any…
Karasic
  • 29
  • 3
2
votes
0 answers

keras Model.fit keeps increasing my memory usage

Why running a DQN, the memory of my program increase at every model.fit() call. using memory_profiler on the train() function in my DQN I get this: Line # Mem usage Increment Occurrences Line…
MrHurricane
  • 21
  • 2
2
votes
1 answer

ValueError: Layer "model_69" expects 3 input(s), but it received 96 input tensors

I am trying not to use model.predict() nor model.fit() in a for loop to speed up training so I'm trying to implement this solution to my case but I get an error. The model has three inputs. This is my code: n_possible_movements = 9 MINIBATCH_SIZE =…
Ness
  • 158
  • 1
  • 12
2
votes
2 answers

Tf-agent Actor/Learner: TFUniform ReplayBuffer dimensionality issue - invalid shape of Replay Buffer vs. Actor update

I try to adapt the this tf-agents actor<->learner DQN Atari Pong example to my windows machine using a TFUniformReplayBuffer instead of the ReverbReplayBuffer which only works on linux machine but I face a dimensional issue. [...] ---> 67…
Sch_Stef
  • 31
  • 4
2
votes
1 answer

OpenAI Gym problem override ObservationWrapper reset() method

I've been trying to solve the pong atari with a DQN. I'm using OpenAI gym for the pong environment. I've made a custom ObservationWrapper but I'm unable to figure out whats the problem with the reset() method I've overriden. Error: Traceback (most…
Levenlol
  • 305
  • 5
  • 17
2
votes
0 answers

Using custom keras model with layer sharing together dqn_agent.DqnAgent()

I am trying to use a custom neural network with the DqnAgent() from tf. In my model I need to use layer sharing. Thus, I use the functional API to build the model. The model has a dict as input and one layer with n neurons as output. The last layer…
Brownie
  • 31
  • 2
1
2 3
…
13 14