Questions tagged [dqn]

For questions related to the deep Q-network (DQN), which is a deep neural network (e.g. a convolutional neural network) trained with a variant of Q-learning. The expression was coined in the paper "Playing Atari with Deep Reinforcement Learning" (2013) by Google's DeepMind.

Filter by
Sorted by
Tagged with
1
vote
0answers
28 views

How should I change the hyper-parameters of the C51 algorithm, in order to obtain higher reward?

I have a scenario where, in an ideal situation, the greedy approach is the best, but when non-idealities are introduced which can be learned, DQN starts doing better. So, after checking what DQN ...
1
vote
1answer
37 views

In reinforcement learning, is it possible to make some actions more likely?

In a general DQN framework, if I have an idea of some actions being better than some other actions, is it possible to make the agent select the better actions more often ?
1
vote
0answers
25 views

What adapts an algorithm to continuous or to discrete action spaces?

Some RL algorithms can only be used for environments with continuous action spaces (e.g TD3, SAC), while others only for discrete action spaces (DQN), and some for both REINFORCE and other policy ...
1
vote
1answer
44 views

Why do we minimise the loss between the target Q values and 'local' Q values?

I have a question regarding the loss function of target networks and current (online) networks. I understand the action value function. What I am unsure about is why we seek to minimise the loss ...
1
vote
0answers
18 views

REINFORCE Agent suddenly drops. How to verify if it's due to catastrophic forgetting?

I am using the default implementations of REINFORCE, DQN and c51 available from the tf.agents repo (links). As you can see, DQN manages to improve performance while REINFORCE seems to suffer from ...
1
vote
0answers
28 views

Should the exploration rate be updated at the end of the episode or at every step?

My agent uses an $\epsilon$-greedy strategy to learn. The exploration rate (i.e. $\epsilon$) decays throughout the training. I've seen examples where people update $\epsilon$ every time an action is ...
1
vote
0answers
47 views

How does one stack multiple observations in the input layer of a convolutional neural network?

The paper, Deep Recurrent Q-Learning for Partially Observable MDPs, talks about stacking multiple observations in the input of a convolutional neural network. How does this exactly work? Do the ...
1
vote
0answers
23 views

Is it feasible to train a DQN with thousands of input ports?

I designed a DQN architecture for some problem. The problem has a parameter $m$ as the number of clients. In my situation, $m$ is large, $m\in\{100,200,\ldots,1000\}$. For this situation, the number ...
1
vote
0answers
23 views

How to train a hierarchical DQN to play the Montezuma's Revenge game?

Would anybody share the experience on how to train a hierarchical DQN to play the Montezuma's Revenge game? How should I design the reward function? How should I balance the anneal rate of the two-...
1
vote
0answers
47 views

Why scaling reward drastically affects performance?

I have devised an gridworld-like environment where a RL agent is tasked to cover all the blank squares by passing through them. Possible actions are up, down, left, right. The reward scheme is the ...
1
vote
1answer
69 views

How is exponential moving average computed in deep Q networks?

In normal Q-learning, the update rule is an implementation of the exponential moving average, which then converges to the optimal true Q values. However, looking at DQN, how exactly is the exponential ...
1
vote
0answers
42 views

How does DQN convergence work in reinforcement learning

In supervised learning we have an unbiased target value, but in reinforcement learning this isn’t the case The network predicts its own target value, now how exactly does it converge if the network ...
1
vote
0answers
32 views

How can deep Q-learning converge if the targets may not be correct?

In deep Q-learning, $Q(s, a)$ and $Q'(s, a)$ are predicted or estimated by the neural network itself. In supervised learning, the target value is a true unbiased value. However, this isn't the case in ...
1
vote
0answers
69 views

What happens if our target network overestimates the value?

When we use DDQN, we often use the target network in case our online network overestimates a value, but this doesn't make sense to me, because What happens if our target network is the one that ...
1
vote
0answers
42 views

How can I build a deep reinforcement learning model that can be trained with multiple time series datasets

I built a DRL model to trade stocks in the financial market but the number of observations is relatively small and I would like to increase it by training the same model with stocks from several ...
1
vote
0answers
71 views

Atari Games: Pretrained CNN to accelerate training?

DQN for Atari takes considerable training time. For example, the 2015 paper in Nature notes that algorithms are trained for 50 million frames or equivalently around 38 days of game experience in total....
1
vote
0answers
42 views

Designing a reward function for my reinforcement learning problem

I'm working on a project lately and I'm trying to solve a problem with reinforcement learning and I have serious issues with shaping the reward function. The problem is designing a device with maximum ...
1
vote
0answers
85 views

Understanding the role of the target network in this DQN algorithm

I've found online this interesting algorithm: From what I understand reading this algorithm, I can't figure out why I should "perform the opposite action" and consequently storing that second ...
1
vote
0answers
39 views

DQN not showing the agent is learning in a snake grid environment game

I've been trying to train a snake for the snake game in DQN. Which the snake can essentially just move up, down, left and right. I'm having a hard time getting the snake to stay alive longer. So my ...
1
vote
1answer
56 views

Is it possible to prove that the target policy is better than the behavioural policy based on learned Q values?

I have retrospective data for a sort of "behaviour policy" which I will use to train a deep q network to learn a target greedy policy. After learning the Q values for this target policy, can we make ...
1
vote
1answer
68 views

Do smaller loss values during DQN training produce better policies?

During the training of DQN, I noticed that the model with prioritized experience replay (PER) had a smaller loss in general compared to a DQN without PER. The mean squared loss was an order of ...
1
vote
1answer
75 views

How does the DQN loss from td_targets against q_values make sense?

Why td_loss is calculated from (td_targets against q_values)? Why I am lost is because: <...
1
vote
0answers
28 views

How can I design a DQN or policy gradient model to explore and collect all optimal solutions?

I am working to use DQN and Policy Gradient reinforcement learning models to solve classic maze escaping problems. So far, I have been able to train a model, which, after around 100 episodes, ...
1
vote
0answers
25 views

Why are Dueling Q Networks not used more often to approximate Q-values in reinforcement learning algorithms?

I've just learned about Dueling Network Architectures to estimate $Q$-values and am wondering why this architecture is not used more often in deep RL algorithms? DDPG and TD3 estimate the $Q$-function ...
1
vote
0answers
156 views

Replace epsilon greedy action selection and the standard DQN by an Independent Gaussian Noise Network Model

Here is my code Recently, I solved the game of Atari Breakout using a classic DQN model. The convergence of the mean reward slowly improved during three days. I was interested in learning a method ...
1
vote
0answers
76 views

Why isn't my DQN agent improving when trained on Atari Breakout?

Lately, I have implemented DQN for Atari Breakout. Here is the code: https://github.com/JeremieGauthier/AI_Exercices/blob/master/Atari_Breakout/DQN_Breakout.py I have trained the agent for over ...
1
vote
1answer
146 views

Can this be a possible deep q learning pseudocode?

I am not using replay here. Can this be a possible deep q learning pseudocode? ...
1
vote
0answers
36 views

Atari Breakout Infrastructure

This is how they describe their infrastructure in https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf. I want to implement the game of Atari Breakout. ...
1
vote
0answers
129 views

What's the difference in using multiple convolutional layers and no pooling versus using a single convolutional layer and a single max pooling layer?

I'm currently working on a college project in which I'm designing a Deep Q-Network that takes images/frames as an input. I've been searching online to see how other people have designed their ...
1
vote
2answers
890 views

Understanding the loss function in deep Q-learning

I am trying to understand how deep Q learning (DQN) works. To my current understanding, each $Q(s, a)$ functions is estimated to be a function of a feature vector of its state $\phi$(s) and the weight ...
1
vote
0answers
37 views

Is the training of multi-version of the same system at the same time affecting the results?

I'm using DQN to train multi-version of the same system and there is a small difference when I run them both separately. However, my result suddenly dropped in both versions if I run them both at the ...
1
vote
0answers
20 views

TD losses are descreasing, but also rewards are decreasing, increasing sigma

I'm using Q-learning with some extensions such as noisy linear layers, n-steps and double DQN. The training, however, isn't that successful, my rewards are descreasing over time after a steep ...
1
vote
0answers
252 views

Why is the $\epsilon$ hyper-parameter (in the $\epsilon$-greedy policy) annealed smoothly?

As far as I understand, RL is a process that can be divided into 2 stages: Exploring a wide range of paths (acting randomly) Refining the current optimal paths (revolving around actions with a so-...
1
vote
0answers
110 views

Online normalization of database for DQN

I have an issue with the normalization of the database (a large time series) for my DQN. I obtained optimal results and saved the NN (5 LSTM layers) weights training on a database normalized as such: ...
1
vote
0answers
24 views

DQN ANN input vs Linear function approximator feature vector

So when using semi-gradient td(0) you need to convert your state representation into a feature vector that represents the state and as far as I know, should not be correlated. Is the input on the ANN ...
1
vote
0answers
40 views

Deciding the rewards for different actions in Pong for a DQN agent

I am attempting to implement an agent that learns to play in the Pong environment, the environment was created in PyGame and I return the pixel data and score at each frame. I use a CNN to take a ...
1
vote
1answer
72 views

DQN Q-values are static

I am working on a DDQN with 5 LSTM layers and 3 actions as output and state space of 21 features. I am dividing the dataset into episodes of 720 timesteps, for each episode the agent acts greedily for ...
1
vote
0answers
88 views

Do we need to reset the DQN network after every episode?

I was going through this implementation of Reinforcement learning where model is being trained to manage the number of bikes at a station. Here, line 78 represents the loop over all episodes (if I ...
1
vote
0answers
37 views

Comparison and understanding of different version of DDQN?

There are several version of DDQN floating around. Sutton gives one that is a simple symmetric random update of the two Q functions. I think other papers (Silver paper for example) use a kind of ...
1
vote
1answer
112 views

Should I ignore the actions RIGHTFIRE and LEFTFIRE in the SpaceInvaders environment? [closed]

I'm trying to replicate the DeepMind DQN paper. I'm using OpenAI's Gym. I'm trying to get a decent score with Space Invaders (using SpaceInvaders-v4 environment). I ...
1
vote
0answers
76 views

Exploration rate decay and training in Q learning

I'm trying to replicate the results of the DeepMind's paper with Breakout included in OpenAI Gym. I wonder how much frames should I keep until I reach the fixed exploration rate. Actually it reaches ...
1
vote
0answers
53 views

Deep Q-Network concepts and implementation

How does sequential DQN work? How would one construct the simple sequential DQN? OpenAI Baselines: DQN
0
votes
1answer
40 views

When calculating the cost in deep Q-learning, do we use both the input and target states?

I just finished Andrew Ngs's deep learning specialization, but RL was not covered, so I don't know the basics of RL. So, I have been having trouble understanding the cost function in deep Q-learning. ...
0
votes
3answers
174 views

For some reasons, a reward becomes a penalty if

I am working to build a reinforcement agent with DQN. The agent would be able to place buy and sell orders for a day trading purpose. I am facing a little problem with that project. The question is "...
0
votes
1answer
186 views

Is DDPG just for deterministic environments?

I want to develop an AI for continuous space. I reached to DDPG algorithm that takes actions deterministically. If DDPG takes actions deterministically, should the environment also be deterministic? ...
0
votes
1answer
20 views

DQN rgb input channels problem using pytorch

I've been trying to learn about CNN's and reinforcement learning and I found this project to play with: https://github.com/adityajn105/flappy-bird-deep-q-learning I've been trying to change the code ...
0
votes
1answer
60 views

How does training for DQN work if messing up in the environment in costly?

Suppose that we want to train a car to drive in the real world and decide to use Reinforcement Learning (specifically, DQN) for that. I am a bit confused about how training generally works. Is it that ...
0
votes
1answer
63 views

How do I know that the DQN has learnt an appropriate Q function?

Is there any sanity check to know whether the Q functions learnt are appropriate in deep Q networks? I know that the Q values for end states should approximate the terminal reward. However, is it ...
0
votes
2answers
112 views

When we use a neural network to approximate the Q values, is the Q target a single value?

I have two questions When we use our network to approximate our Q values, is the Q target a single value? During backpropagation, when the weights are updated, does it automatically update the Q ...
0
votes
1answer
790 views

DQN it's not working properly

I'm trying to build a DQN to replicate the DeepMind results. I'm doing with a simple DQN for the moment, but it isn't learning properly: after +5000 episodes, it couldn't get more than 9-10 points. ...