DQN is a multi-layered neural network, added target network and experience replay to Q-learning
Questions tagged [dqn]
206 questions
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
0 answers
Why does my DQN model makes obviously wrong decisions?
I have tried to realize a simple turn-based snake game played by a tensorflow model in python:
The agent can move on a board (e.g. 40x40 cells) leaving a trail at each visited cell. In each round the agent has to choose one of three possible actions…
coccyxx
- 1
0
votes
1 answer
Reinforcement learning DQN environment structure
I am wondering how best to feed back the changes my DQN agent makes on its environment, back to itself.
I have a battery model whereby an agent can observe a time-series forecast of 17 steps, and 5 features. It then makes a decision on whether to…
CarterB
- 502
- 1
- 3
- 13
0
votes
0 answers
Using GPU for reinforcement learning with Keras
I am using this code (please excuse its messiness) to run on my CPU. I have a custom RL environment that I have created myself and I am using DQN agent.
But when I run this code on GPU, it doesn't utilize much of it and in fact it is slower than my…
M. Awais Jadoon
- 35
- 10
0
votes
1 answer
DQN with policy and target networks doesn't learn properly on LunarLander enviroment
I'm trying to get a hang of reinforcement learning, so I'm following a guide at:
pytorch.org/tutorials/
They've implemented DQN that solves CartPole with computer vision. Basically, I've copied their code and modified it to solve the LunarLander…
DanielSpory
- 1
- 2
0
votes
2 answers
Deep Reinforcement Learning Motion in Observation
I am trying to implement a DRL (Deep Reinforcement Learning) Agent for self-driving vehicles. I am currently teaching my agent not to bump on other cars, using a simple camera. There are many ways to speed up the training, but currently, I am…
LazyAnalyst
- 426
- 3
- 16
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 implement gradient ascent in a Keras DQN
Have built a Reinforcement Learning DQN with variable length sequences as inputs, and positive and negative rewards calculated for actions. Some problem with my DQN model in Keras means that although the model runs, average rewards over time…
MarkD
- 395
- 3
- 14
0
votes
1 answer
Multiagent (not deep) reinforcement learning? Modeling the problem
I have N number of agents/users accessing a single wireless channel and at each time, only one agent can access the channel and receive a reward.
Each user has a buffer that can store B number of packets and I assume it as infinite buffer.
Each user…
M. Awais Jadoon
- 35
- 10
0
votes
1 answer
DQN agent with vector input and vector output
I am a beginner at Reinforcement Learning and Deep Learning and I want to built a neural network for a DQN agent (in Keras) that receives a vector as input of length equal to 3 and outputs another vector of length equal to 10.
The input vector has…
Ness
- 158
- 1
- 12
0
votes
2 answers
Keras CNN for non-image matrix
I have recently started learning about Deep Learning and Reinforcement Learning, and I am trying to figure out how to code a Convolutional Neural Network using Keras for a matrix of 0s and 1s with 10 rows and 3 columns.
The input matrix would look…
Ness
- 158
- 1
- 12
0
votes
1 answer
Problem having the right input for model.predict() in Keras model
I have a DQN agent, that receives a state composed of a numerical value indicating its position and a 2D array denoting the requests from a number of users.
My attempt of architecting the neural network was as described here.
Model Summary
The…
Ness
- 158
- 1
- 12
0
votes
1 answer
Can I train an agent without interactions with environment using DQN and samples?
I want to train an RL agent without interactions with the environment using DQN and samples.
In my understanding, DQN is an off-policy algorithm so that it seems possible. (Am I right?)
However, I've failed to train so far. Specifically, the value…
0
votes
1 answer
Can I train DQN without updating training agent?
I'm a newbie in RL so please forgive me if I ask stupid question:)
I'm working a DQN project right now and it's very similar to the simplest snake game. The game is wrote in js and has a demo (in which snake moves randomly). But since I don't know…
陈元坤
- 1
0
votes
1 answer
Deep Q-Learning for grid world
Has anyone implemented the Deep Q-learning to solve a grid world problem where state is the [x, y] coordinates of the player and goal is to reach a certain coordinate [A, B]. Reward setting could be -1 for each step and +10 for reaching [A,B]. [A,…
corvo
- 676
- 2
- 7
- 20