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
2
votes
1answer
109 views

Updating action-value functions in Semi-Markov Decision Process and Reinforcement Learning

Suppose that the transition time between two states is a random variable (for example, unknown exponential distribution); and between two arrivals, there is no reward. If $\tau$ (real number not an ...
3
votes
2answers
107 views

Why is it not advisable to have a 100 percent exploration rate? [duplicate]

During the learning phase, why don't we have a 100% exploration rate, to allow our agent to fully explore our environment and update the Q values, then during testing we bring in exploitation? Does ...
2
votes
1answer
54 views

Why isn't it wise for us to completely erase our old Q value and replace it with the calculated Q value?

Why isn't it wise for us to completely erase our old Q value and replace it with the calculated Q value? Why can't we forget the learning rate and temporal difference? Here's the update formula.
1
vote
1answer
484 views

What's the best practice for Boltzmann Exploration temperature in RL?

I'm currently modeling DQN in Reinforcement Learning. My question is: what are the best practices related to Boltzmann Exploration? My current thoughts are: (1) Let the temperature decay through ...
1
vote
1answer
60 views

Why do we update the weights of the target network in deep Q learning?

I know we keep the target network constant during training to improve stability, but why exactly are we updating the weights of our target network? In particular, if we've already reached convergence, ...
1
vote
2answers
58 views

Why do we explore after we have an accurate estimate of the value function?

Suppose we have a small space state and that, after about 2000 episodes, we've accurately explored the environment and known the accurate $Q$ values. In that case, why do we still leave a small ...
6
votes
2answers
1k views

Does using the softmax function in Q learning not defeat the purpose of Q learning?

It is my understanding that, in Q-learning, you are trying to mimic the optimal $Q$ function $Q*$, where $Q*$ is a measure of the predicted reward received from taking action $a$ at state $s$ so that ...
1
vote
1answer
72 views

What would happen if we sampled only one tuple from the experience replay?

The concept of experience replay is saving our experiences in our replay buffer. We select at random to break the correlation between consecutive samples, right? What would happen if we calculate our ...
0
votes
1answer
199 views

How to validate that my DQN hyperparameters are the optimal?

My DQN model outputs the best traffic light state in an intersection. I used different values of batch size and learning rate to find the best model. How would I know if I got the optimal ...
1
vote
0answers
39 views

Is there a way to show convergence of DQN other than by eye observation?

I made a DQN model and plot its reward curve. You can see intuitively that the curve already converged since its reward value now just oscillates. How can I show confidence that my DQN already reached ...
3
votes
1answer
80 views

How to know if my DQN is optimized?

I made a DQN that controls a traffic light. The observation states are the number of vehicles of each lane in the intersection. I trained it for 500 episodes and saved the model every 50th episode. I ...
1
vote
2answers
78 views

Why can't we fully exploit the environment after the first episode in Q-learning?

During the first episode, it's 100% exploration, because all our Q values are 0. Suppose we have 1000 time steps, and it's terminated by meeting a reward. So, after the first episode, why can't we ...
1
vote
1answer
177 views

What are the differences between SARSA and Q-learning?

From Sutton and Barto's book Reinforcement Learning (Adaptive Computation and Machine Learning series), are the following definitions: To aid my learning of RL and gain an intuition, I'm focusing on ...
3
votes
1answer
237 views

Why we don't use importance sampling in tabular Q-Learning?

Why don't we use an importance sampling ratio in Q-Learning, even though Q-Learning is an off-policy method? Importance sampling is used to calculate expectation of a random variable by using data ...
1
vote
2answers
72 views

Generalising performance of Q-learning agent through self-play in a two-player game (MCTS?)

I'm using Q-learning (off-policy TD-control as specified in Sutton's book on pg 131) to train an agent to play connect four. My goal is to create a strong player (superhuman performance?) purely by ...
0
votes
1answer
81 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 ...
1
vote
1answer
121 views

Why do my rewards fall using tabular Q-learning as I perform more episodes?

Using the tutorial from: SentDex - Python Programming I added Q Learning to my script that was previously just picking random actions. His script uses the MountainCar Environment so I had to amend it ...
0
votes
2answers
220 views

Help with deep Q learning for 2048 game getting stuck

I am having trouble making a reinforcement algorithm than can win the 2048 game. I have tried with deep Q (which I think is the simplest algorithm that should be able to learn a winning strategy). ...
0
votes
2answers
144 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 ...
2
votes
0answers
100 views

If the minimum Q value is decreasing and the maximum Q value increasing, is this a sign that dueling double DQN is diverging?

I'm training a dueling double DQN agent with prioritized replay buffer and notice that the min Q values are decreasing, while the max Q values are increasing. Is this a sign that it is diverging? ...
3
votes
0answers
83 views

How to take actions at each episode and within each step of the episode in deep Q learning?

In deep Q learning, we execute the algorithm for each episode, and for each step within an episode, we take an action and record a reward. I have a situation where my action is 2-tuple $a=(a_1,a_2)$. ...
2
votes
0answers
42 views

In a DQN, can Prioritized Experience Replay actually perform worse than a regular Experience Replay?

I've written a Double DQN-based stock trading bot using mainly time series stock data. I've recently upgraded my Experience Replay(ER) code with a version of Prioritized Experience Replay (PER) ...
2
votes
0answers
78 views

How can the target rely on untrained parameters?

I'm trying to understand DQN. I understand where the loss function comes from. I'm just unsure about why the target function works in practice. Given the loss function $$ L_i(\theta_i) = [(y_i - Q(s,a;...
1
vote
1answer
129 views

Can tabular Q-learning converge even if it doesn't explore all state-action pairs?

My understanding of tabular Q-learning is that it essentially builds a dictionary of state-action pairs, so as to maximize the Markovian (i.e., step-wise, history-agnostic?) reward. This incremental ...
2
votes
0answers
48 views

Are the final states not being updated in this $n$-step Q-Learning algorithm?

I am reading this paper and in algorithm 3 they describe an $n$-step Q-Learning algorithm. Below is the pseudo-code. From this pseudo-code, it looks as though the final tuples that they would ...
1
vote
1answer
104 views

Handle non-existing states in q-learning

I am using Q-learning to solve an engineering problem. The objective is to generate a Q-table associating state to Q-values. I created a State vector ...
2
votes
0answers
81 views

How to prevent deep Q-learning algorithms to overfit?

I have recently solved the Cartpole problem using double deep Q-learning. When I saw how the agent was doing, it used to go right every time, never left, and it did similar actions all the time. Did ...
1
vote
1answer
85 views

If deep Q-learning starts to choose only one action, is this a sign that the algorithm diverged?

I'm working on a deep q-learning model in an infinite horizon problem, with a continous state space and 3 possible actions. I'm using a neural network to approximate the action-value function. ...
4
votes
2answers
647 views

Is there any good reference for double deep Q-learning?

I am new in reinforcement learning, but I already know deep Q-learning and Q-learning. Now, I want to learn about double deep Q-learning. Do you know any good references for double deep Q-learning? ...
2
votes
1answer
248 views

How should I decay $\epsilon$ in Q-learning?

How should I decay the $\epsilon$ in Q-learning? Currently, I am decaying epsilon as follows. I initialize $\epsilon$ to be 1, then, after every episode, I multiply it by some $C$ (let it be $0.999$)...
1
vote
1answer
527 views

How and when should we update the Q-target in deep Q-learning?

I have recently watched David silver's course, and started implementing the deep Q-learning algorithm. I thought I should make a switch between the Q-target and Q-current directly (meaning, every ...
2
votes
1answer
76 views

Is the PyTorch official tutorial really about Q-learning?

I read Q-learning algorithm and also I know value iteration (when you update action values). I think the PyTorch example is value iteration rather than Q-learning. Here is the link: https://pytorch....
3
votes
0answers
62 views

Convergence of a delayed policy update Q-learning

I thought about an algorithm that twists the standard Q-learning slightly, but I am not sure whether convergence to the optimal Q-value could be guaranteed. The algorithm starts with an initial ...
1
vote
1answer
385 views

Can we increase the speed of training a reinforcement learning algorithm?

I am new in reinforcement learning. I started reading the PyTorch's documentation about the cart pole control. Whenever an agent fails, they restart the environment. When I run the code, the time in ...
2
votes
2answers
382 views

How does Monte Carlo Exploring Starts work?

I'm having trouble understanding the 5th step in the flowchart. For the 5th step, the 'update the Q function by taking the average of returns' is confusing. From what I understand, the Q function ...
1
vote
1answer
47 views

Do we have two Q-learning update formulas?

I have seen two deep Q-learning formulas: $$Q\left(S_{t}, A_{t}\right) \leftarrow Q\left(S_{t}, A_{t}\right)+\alpha\left[R_{t+1}+\gamma \max _{a} Q\left(S_{t+1}, a\right)-Q\left(S_{t}, A_{t}\right)\...
0
votes
1answer
38 views

How to add more than 1 agent in one generation with Q Learning

Sometimes the agent learns a bit slow and you want to have multiple agents in one generation. And at each episode you'll draw on the screen only the best of them or all of them. How is that possible? ...
1
vote
1answer
213 views

How can I model and solve the Knight Tour problem with reinforcement learning?

I've read about the Knight Tour problem. And I wanted to try to solve it with a reinforcement learning algorithm with OpenAI's gym. So, I want to make a bot that can move on the chess table like the ...
3
votes
1answer
104 views

What is the difference between on-policy and off-policy for continuous environments?

I'm trying to understand RL applied to time series (so with infinite horizon) which have a continous state space and a discrete action space. First, some preliminary questions: in this case, what is ...
11
votes
2answers
1k views

How do we prove the n-step return error reduction property?

In section 7.1 (about the n-step bootstrapping) of the book Reinforcement Learning: An Introduction (2nd edition), by Andrew Barto and Richard S. Sutton, the authors write about what they call the "n-...
3
votes
1answer
99 views

Does Q Learning learn from an opponent playing random moves?

I've created a Q Learning algorithm to play Connect Four against an opponent who just chooses a random free column. My Q Agent is currently only winning about 0.49 games on average (30,000 episodes). ...
1
vote
1answer
37 views

Applying Eligibility Traces to Q-Learning algorithm does not improve results (And might not function well)

I am trying to apply Eligibility Traces to a currently working Q-Learning algorithm. The reference code for the Q-Learning algorithm was taken from this great blog ...
1
vote
1answer
39 views

Should I just use exploitation after I have trained the Q agent?

When using a trained Q-learning algorithm in an actual game, would I just use exploitation and no longer use exploration? Should I use exploration only during the training phase?
1
vote
0answers
37 views

Is Q-Learning suitable for time-dependent spaces?

Many Q-learning techniques have been developed to capture discrete state(observation), actions like a robot in a grid world, and even continuous (state or action) spaces. But I am wondering how we can ...
1
vote
0answers
20 views

Why is expected sarsa algorithm an off-policy learning? [duplicate]

I am not able to understand why expected sarsa algorithm is an off-policy learning method? How is it that behaviour and target policies can be different? Also please tell under what situation and ...
1
vote
0answers
32 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 ...
32
votes
2answers
13k views

What is the relation between Q-learning and policy gradients methods?

As far as I understand, Q-learning and policy gradients (PG) are the two major approaches used to solve RL problems. While Q-learning aims to predict the reward of a certain action taken in a certain ...
2
votes
2answers
209 views

Is my understanding of the value function, Q function, policy, reward and return correct?

I'm a beginner in the RL field, and I would like to check that my understanding of certain RL concepts. Value function: How good it is to be in a state S following policy π. ...
3
votes
0answers
30 views

Relationship between the reward rate and the sampled reward in a Semi-Markov Decision Process

In the paper: Reinforcement learning methods for continuous-time Markov decision problems, the authors provide the following update rule for the Q-learning algorithm, when applied to Semi-Markov ...

1 2 3
4
5
7