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
5
votes
1answer
191 views

Why does Q-learning converge under 100% exploration rate?

I am working on this assignment where I made the agent learn state-action values (Q-values) with Q-learning and 100% exploration rate. The environment is the classic gridworld as shown in the ...
3
votes
1answer
75 views

Why can we take the action $a$ from the next state $s'$ in the max part of the Q-learning update rule, if that action doesn't lead to any reward?

I'm using OpenAI's cartpole environment. First of all, is this environment not Markov? Knowing that, my main question concerns Q-learning and off-policy methods: For me, there is something weird in ...
0
votes
0answers
24 views

How DynaQ behaves in stochastic world in comparison with other reinforcement learning algorithms?

I came across of implementations of a bunch of algorithms on stochastic windy gridworld. This is the graph comparing their performance: So clearly, it seems that DynaQ performs better than all other ...
2
votes
2answers
62 views

Should we feed a greater fraction of terminal states to the value network so that their values are learned first?

The basis of Q-learning is recursive (similar to dynamic programming), where only the absolute value of the terminal state is known. Shouldn't it make sense to feed the model a greater proportion of ...
1
vote
1answer
65 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 ...
5
votes
3answers
465 views

In Q-learning, wouldn't it be better to simply iterate through all possible states?

In Q-learning, all resources I've found seem to say that the algorithm to update the Q-table should start at some initial state, and pick actions (which are sometimes random) to explore the state ...
3
votes
1answer
603 views

Why does Deep Q Network outputs multiple Q values?

I am learning Deep RL following this tutorial: https://medium.freecodecamp.org/an-introduction-to-deep-q-learning-lets-play-doom-54d02d8017d8 I understand everything but one detail: This image shows ...
5
votes
3answers
1k views

What is a high dimensional state in reinforcement learning?

In the DQN paper, it is written that the state-space is high dimensional. I am a little bit confused about this terminology. Suppose my state is a high dimensional vector of length $N$, where $N$ is a ...
2
votes
2answers
123 views

What is the target output for updating a Deep Q Network

I'm trying to implement Deep Q-Learning for a pet problem having a continuous state space and discretized action space. The algorithm for table-based Q-Learning updates a single entry of the Q table - ...
5
votes
1answer
647 views

What are good learning strategies for Deep Q-Network with opponents?

I am trying to find out what are some good learning strategies for Deep Q-Network with opponents. Let's consider the well-known game Tic-Tac-Toe as an example: How should an opponent be implemented ...
0
votes
1answer
59 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,...
6
votes
2answers
626 views

Can DQN perform better than Double DQN?

I'm training both DQN and double DQN in the same environment, but DQN performs significantly better than double DQN. As I've seen in the double DQN paper, double DQN should perform better than DQN. Am ...
2
votes
1answer
185 views

What is a “learned policy” in Q-learning?

I am completing an assignment at the moment. One of the assignment questions asks how you identified the learned policy and how you obtained it. The question is a reinforcement learning question, and ...
3
votes
2answers
151 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
394 views

Proof of Maximization Bias in Q-learning?

In the textbook "Reinforcement Learning: An Introduction" by Richard Sutton and Andrew Barto, the concept of Maximization Bias is introduced in section 6.7, and how Q-learning "over-estimates" action-...
0
votes
1answer
100 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
0answers
28 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}(\...
5
votes
3answers
1k views

What is the target Q-value in DQNs?

I understand that in DQNs, the loss is measured by taking the MSE of outputted Q-values and target Q-values. What does the target Q-values represent? And how is it obtained/calculated by the DQN?
3
votes
1answer
317 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 ...
0
votes
2answers
217 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 ...
3
votes
1answer
824 views

Deep Q-Learning poor convergence on Stochastic Environment

I'm trying to implement a Deep Q-network in Keras/TF that learns to play Minesweeper (our stochastic environment). I have noticed that the agent learns to play the game pretty well with both small and ...
1
vote
2answers
2k views

Q Learning Algorithm not converging

I am trying to run Deep Q-learning algorithm on a game which I made in Python using pygame library. The algorithm accepts the game screen (4 frames) as input to neural network which used as the ...
0
votes
0answers
60 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
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 ...
0
votes
0answers
50 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 ...
1
vote
1answer
81 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 ...
17
votes
3answers
2k views

Why doesn't Q-learning converge when using function approximation?

The tabular Q-learning algorithm is guaranteed to find the optimal $Q$ function, $Q^*$, provided the following conditions (the Robbins-Monro conditions) regarding the learning rate are satisfied $\...
6
votes
1answer
166 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 ...
10
votes
1answer
590 views

Are Q-learning and SARSA the same when action selection is greedy?

I'm currently studying reinforcement learning and I'm having difficulties with question 6.12 in Sutton and Barto's book. Suppose action selection is greedy. Is Q-learning then exactly the same ...
2
votes
1answer
68 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
112 views

When training a DQN, how should we update the value of actions that were not taken?

Let's say that we have three actions. The highest-valued action of the three choices is the first. When training the DQN, what do we do with the other two, as we don't have a target for them, since ...
1
vote
1answer
3k views

What is the difference between the $\epsilon$-greedy and softmax policies?

Could someone explain to me which is the key difference between the $\epsilon$-greedy policy and the softmax policy? In particular, in the contest of SARSA and Q-Learning algorithms. I understood the ...
2
votes
2answers
268 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
1k views

Why are Q values updated according to the greedy policy?

Apparently, in the Q-learning algorithm, the Q values are not updated according to the "current policy", but according to a "greedy policy". Why is that the case? I think this is related to the fact ...
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 ...
2
votes
1answer
73 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,...
3
votes
1answer
93 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
96 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 ...
11
votes
2answers
5k views

Can Q-learning be used for continuous (state or action) spaces?

Many examples work with a table-based method for Q-learning. This may be suitable for a discrete state (observation) or action space, like a robot in a grid world, but is there a way to use Q-learning ...
2
votes
1answer
55 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 ...
8
votes
1answer
2k views

What are other ways of handling invalid actions in scenarios where all rewards are either 0 (best reward) or negative?

I created an OpenAI Gym environment, and I would like to check the performance of the agent from OpenAI Baselines DQN approach on it. In my environment, the best possible outcome for the agent is 0 - ...
5
votes
1answer
95 views

How should I handle invalid actions in a grid world?

I'm building a really simple experiment, where I let an agent move from the bottom-left corner to the upper-right corner of a $3 \times 3$ grid world. I plan to use DQN to do this. I'm having trouble ...
6
votes
1answer
4k views

How to implement exploration function and learning rate in Q Learning

I'm trying to implement Q-learning (state-based representation and no neural / deep stuff) but I'm having a hard time getting it to learn anything. I believe my issue is with the exploration function ...
14
votes
1answer
3k views

Why does DQN require two different networks?

I was going through this implementation of DQN and I see that on line 124 and 125 two different Q networks have been initialized. From my understanding, I think one network predicts the appropriate ...
3
votes
1answer
99 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 ...
2
votes
1answer
392 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 ...
3
votes
1answer
765 views

Why is my implementation of Q-learning not converging to the right values in the FrozenLake environment?

I am trying to learn tabular Q learning by using a table of states and actions (i.e. no neural networks). I was trying it out on the FrozenLake environment. It's a very simple environment, where the ...
3
votes
1answer
391 views

How do we compute the target value when the agent ends up in the terminal state?

I am working on a deep reinforcement learning problem. Throughout the episode, there is a small positive and negative reward for good or bad decisions. In the end, there is a huge reward for the ...

1
2
3 4 5
7