Questions tagged [q-learning]

For questions related to the Q-learning algorithm, which is a model-free and temporal-difference reinforcement learning algorithm that attempts to approximate the Q function, which is a function that, given a state s and an action a, returns a real number that represents the return (or value) of state s when action a is taken from s. Q-learning was introduced in the PhD thesis "Learning from Delayed Rewards" (1989) by Watkins.

Filter by
Sorted by
Tagged with
0
votes
1answer
61 views

Relationship between Rewards and Q Value (Graph between Q(s, a) vs episodes)

I'm employing the Actor-Critic algorithm. The critic network approximates the action-value function, i.e. $Q(s, a)$, which determines how good a particular state is, when provided with an action. $Q(s,...
9
votes
2answers
2k views

What is the difference between Q-learning, Deep Q-learning and Deep Q-network?

Q-learning uses a table to store all state-action pairs. Q-learning is a model-free RL algorithm, so how could there be the one called Deep Q-learning, as deep means using DNN; or maybe the state-...
2
votes
0answers
29 views

Is better to reward short- or long-term progress in Q-learning?

I have been training some kind of agent to reach a target using a Q-learning based approach, and I have tried two different types of rewards: Long-term reward: $\mathrm{reward} = - \mathrm{distance}(\...
0
votes
1answer
111 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. ...
2
votes
1answer
142 views

Offline/Batch Reinforcement Learning: when to stop training and what agent to select

Context: My team and I are working on a RL problem for a specific application. We have data collected from user interactions (states, actions, rewards, etc.). It is too costly for us to emulate agents....
4
votes
1answer
403 views

Why does regular Q-learning (and DQN) overestimate the Q values?

The motivation for the introduction of double DQN (and double Q-learning) is that the regular Q-learning (or DQN) can overestimate the Q value, but is there a brief explanation as to why it is ...
5
votes
1answer
121 views

Research into social behavior in Prisoner's Dilemma

I've been working on research into reproducing social behavior using multi-agent reinforcement learning. My focus has been on a GridWorld-style game, but I was thinking that maybe a simpler Prisoner's ...
0
votes
2answers
326 views

Simple DQN too slow to train [closed]

I have been trying to solve the OpenAI lunar lander game with a DQN taken from this paper https://arxiv.org/pdf/2006.04938v2.pdf The issue is that it takes 12 hours to train 50 episodes so something ...
0
votes
0answers
64 views

Is there any toy example that can exemplify the performance of double Q-learning?

I recently tried to reproduce the results of double Q-learning. However, the results are not satisfying. I have also tried to compare double Q learning with Q-learning in Taxi-v3, FrozenLake without ...
1
vote
1answer
101 views

How to build a Neural Network to approximate the Q-function?

I am learning reinforcement learning with Q-learning using online resources, like blog posts, youtube videos, and books. At this point, I have learned the underpinning concepts of reinforcement ...
0
votes
0answers
52 views

Why convergence is not guaranteed when using approximation? [duplicate]

I am doing self study of Reinforcement Learning with Q-learning using online resources like blog posts, youtube videos and books and at this point, I have learned the underpinning concepts of ...
6
votes
1answer
200 views

How is the DQN loss derived from (or theoretically motivated by) the Bellman equation, and how is it related to the Q-learning update?

I'm doing a project on Reinforcement Learning. I programmed an agent that uses DDQN. There are a lot of tutorials on that, so the code implementation was not that hard. However, I have problems ...
1
vote
1answer
69 views

If $\alpha$ decreases over time, why is Q-learning guaranteed to converge?

Q-Learning is guaranteed to converge if $\alpha$ decreases over time. On page 161 of the RL book by Sutton and Barto, 2nd edition, section 8.1, they write that Dyna-Q is guaranteed to converge if each ...
2
votes
2answers
274 views

What happens when the agent faces a state that never before encountered?

I have a network with nodes and links, each of them with a certain amount of resources (that can take discrete values) at the initial state. At random time steps, a service is generated, and, based on ...
0
votes
1answer
54 views

Why is the policy implied by Q-learning deterministic, when it always chooses the action with highest probability?

Q-learning uses the maximizing value at each step, which implies that there is a probability distribution and it happens to choose the one with the highest probability. There is no direct mapping ...
0
votes
0answers
36 views
2
votes
1answer
69 views

Do I need to know in advance all possible number of states in Q-Learning?

In Q-learning, is it mandatory to know all possible states that can the agent may end up in? I have a network with 4 source nodes, 3 sink nodes, and 4 main links. The initial state is the status ...
2
votes
1answer
85 views

What constitutes a large space state (in Q-learning)?

I know this might be specific to different problems, but does anyone know if there is any rule of thumb or references on what constitutes a large state space? I know that, according to multiple papers,...
1
vote
0answers
29 views

How to compute the Retrace target for multi-step off-policy Reinforcement Learning?

I am implementing the A3C algorithm and I want to add off-policy training using Retrace but I am having some trouble understanding how to compute the retrace target. Retrace is used in combination ...
3
votes
1answer
95 views

Why does off-policy learning outperform on-policy learning?

I am self-studying about Reinforcement Learning using different online resources. I now have a basic understanding of how RL works. I saw this in a book: Q-learning is an off-policy learner. An off-...
2
votes
1answer
135 views

What should the value of epsilon be in the Q-learning?

I am trying to understand Reinforcement Learning and already explored different Youtube videos, blog posts, and Wikipedia articles. What I don't understand is the impact of $\epsilon$. What value ...
2
votes
1answer
71 views

Can we use Q-learning update for policy evaluation (not control)?

For policy evaluation purposes, can we use the Q-learning algorithm even though, technically, it is meant for control? Maybe like this: Have the policy to be evaluated as the behaviour policy. Update ...
0
votes
0answers
53 views

How to use Deep Q-Network with two-dimensional input? Hands-on Machine Learning 2

I'm studying with the book Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow, and I'm trying to implement the Deep Q-Network example that can be found on Github but that the input ...
1
vote
0answers
55 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 ...
0
votes
1answer
93 views

Q-learning agent stuck at taking same actions

I have created my own RL environment where I have a 2-dimensional matrix as a state space, the rows represent the users that are asking for a service, and 3 columns representing 3 types of users; so ...
1
vote
1answer
121 views

How to create a Q-Learning agent when we have a matrix as an action space?

I have a 2-dimentional matrix as an action space, the rows being a resource to be allocated, and the columns are the users that we will allocate the resources to. (I built my own RL environment) The ...
1
vote
1answer
66 views

In the definition of the state-action value function, what is the random variable we take the expectation of?

I know that $$\mathbb{E}[g(X) \mid A] = \sum\limits_{x} g(x) p_{X \mid A}(x)$$ for any random variable $X$. Now, consider the following expression. $$\mathbb{E}_{\pi} \left[ \sum \limits_{k=0}^{\infty}...
3
votes
1answer
360 views

How to determine if Q-learning has converged in practice?

I am using Q-learning and SARSA to solve a problem. The agent learns to go from the start to the goal without falling in the holes. At each state, I can choose the action corresponding to the maximum ...
1
vote
1answer
224 views

Reinforcement learning simple problem: agent not learning, wrong action

I am pretty new to RL and I am trying to code a simple RL task with pytorch. The goal/task is the following: The initial state is $t_o$ and the agent takes an action $\Delta_t$: $t_o +\Delta_t = t_1$. ...
3
votes
1answer
69 views

Can we stop training as soon as epsilon is small?

I'm new to reinforcement learning. As it is common in RL, $\epsilon$-greedy search for the behavior/exploration is used. So, at the beginning of the training, $\epsilon$ is high, and therefore a lot ...
1
vote
1answer
204 views

Why do my rewards reduce after extensive training using D3QN?

I am running a drone simulator for collision avoidance using a slight variant of D3QN. The training is usually costly (runs for at least a week) and I have observed that reward function gradually ...
1
vote
2answers
151 views

How does one know that a problem is "model-free" in reinforcement learning?

Consider this slide from a Stanford lecture on reinforcement learning. It states that a model is the agent's representation of how the world changes in response to the agent's action. I've been ...
2
votes
3answers
75 views

DQN not learning and step not stepping towards target

I am trying to create a simple Deep Q-Network with 2d convolutional layers. I can't figure out what I am doing wrong, and the only thing I can see that doesn't seem right is when I get the model ...
2
votes
0answers
62 views

Handling a Large Discrete Action Space in Deep Q Learning

I am attempting to solve a timetabling problem using deep Q learning. It could be thought of as a resource allocation problem to obtain some certificate of 'optimality'. However, how to define and ...
1
vote
0answers
25 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
1answer
54 views

What is the optimal exploration-exploitation trade-off in Q*bert?

I am training an RL agent with Deep Q-learning + Experience Replay on the Q*bert Atari environment. After 400,000 frames, my agent appears to have learned strategic information about the game, but ...
3
votes
2answers
171 views

How to apply Q-learning when rewards is only available at the last state?

I have a scheduling problem in which there are $n$ slots and $m$ clients. I am trying to solve the problem using Q-learning so I have made the following state-action model. A state $s_t$ is given by ...
3
votes
1answer
105 views

Why is sampling non-uniformly from the replay memory an issue? (Prioritized experience replay)

I can't seem to understand why we need importance sampling in prioritized experience replay (PER). The authors of the paper write on page 5: The estimation of the expected value with stochastic ...
3
votes
1answer
258 views

Is there a logical method of deducing an optimal batch size when training a Deep Q-learning agent with experience replay?

I am training an RL agent using Deep-Q learning with experience replay. At each frame, I am currently sampling 32 random transitions from a queue which stores a maximum of 20000 and training as ...
2
votes
1answer
28 views

How is weighted average computed in Deep Q networks

I was going through the Sutton book and they said the update formula for Q learning comes from the weighted average of the returns I.e New estimate= old estimate +alpha*[returns- old estimate] So by ...
3
votes
1answer
1k views

What are the differences between Q-Learning and A*?

Q-learning seems to be related to A*. I am wondering if there are (and what are) the differences between them.
3
votes
1answer
106 views

How to compute the target for double Q-learning update step?

I've already read the original paper about double DQN but I do not find a clear and practical explanation of how the target $y$ is computed, so here's how I interpreted the method (let's say I have 3 ...
1
vote
0answers
30 views

Customized food for persons based on their profile using Reinforcement learning

I am newbie to Reinforcement Learning, this is my idea - Agent(food provider) has to select a food based on the environment(based on the user profile). Here the reward will be given to the agent based ...
2
votes
1answer
73 views

When using experience replay in reinforcement learning, which state is used for training?

I'm slightly confused about the experience replay process. I understand why we use batch processing in reinforcement learning, and from my understanding, a batch of states is input into the neural ...
2
votes
0answers
66 views

Should I use the discounted average reward as objective in a finite-horizon problem?

I am new to reinforcement learning, but, for a finite horizon application problem, I am considering using the average reward instead of the sum of rewards as the objective. Specifically, there are a ...
4
votes
1answer
314 views

When do SARSA and Q-Learning converge to optimal Q values?

Here's another interesting multiple-choice question that puzzles me a bit. In tabular MDPs, if using a decision policy that visits all states an infinite number of times, and in each state, randomly ...
1
vote
0answers
58 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
35 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 ...
3
votes
1answer
465 views

What exactly is the advantage of double DQN over DQN?

I started looking into the double DQN (DDQN). Apparently, the difference between DDQN and DQN is that in DDQN we use the main value network for action selection and the target network for outputting ...
0
votes
0answers
65 views

Strange behavior of Q-learning agent after being trained

I built a simple X*Y grid world environment to learn and then trained my agent over it. All worked fine and the agent learned as well. Let me give some detail about the environment. Environment: A ...

1
2
3 4 5
7