Questions tagged [convergence]

For questions related to the convergence of AI algorithms.

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

Training a neural network simultaneously with two different loss functions rather than considering the weighted sum

This is a follow up on the already asked question: Is the neural network 100% accurate on training data if epoch loss is minimized to 0? I want to train a neural network that works as an approximator ...
  • 111
3 votes
1 answer
29 views

Learning an identity function with convolutional networks

I am trying to train networks to achieve what I expected to be a trivial task: learn the identity mapping. However, this is very hard to achieve, and the optimization is hard. Moreover, I don't want ...
1 vote
2 answers
163 views

Should PPO always converge toward the global optimum?

I'm trying to "solve" the OpenAI gym environment "Humanoid-v3" using PPO. I got it to work to some degree (The NN is learning a policy and perfecting it. Average reward of about 5....
  • 13
3 votes
1 answer
65 views

Is there any variant of perceptron convergence algorithm that ensures uniqueness?

The perceptron convergence algorithm given below ensures the convergence of weights of the perceptron provided enough data points and iterations. Although it ensures convergence by finally getting a ...
  • 3,251
2 votes
1 answer
87 views

Is it possible learning convergence is lost in Reinforcement Learning as the state space grows?

I am new in the AI field and I am trying to use Reinforcement Learning. Specifically, I am using tabular Q-Learning and SARSA algorithms to solve a sequential decision making problem. (I am using <...
  • 33
0 votes
0 answers
27 views

Neural Network learning XOR. I collected Data on my networks convergence. Is this expected behavior?

I build a neural network from scratch to get a better understanding of the fundamentals of machine learning. The network contains a bias for each neuron and calculates the final error via the mean ...
  • 101
2 votes
0 answers
57 views

Do learning rate schedulers conflict with or prevent convergence of the Adam optimiser?

An article on https://spell.ml says Because Adam manages learning rates internally, it's incompatible with most learning rate schedulers. Anything more complicated than simple learning warmup and/or ...
  • 21
0 votes
1 answer
351 views

Why and how can the policy and value iteration methods converge to the OPTIMAL point?

I am reading Reinforcement Learning: An Introduction by Sutton & Barto. According to this textbook, as far as I understood, the authors claim that the policy and value iteration methods converge ...
  • 103
0 votes
3 answers
73 views

What can I infer if my model is converging extremely fast?

I am running a model with fixed hyperparameters. To my surprise/shock, the model converged extremely fast with the least loss possible. I want to know the causes of this phenomenon. I have the ...
  • 3,251
0 votes
0 answers
34 views

dDQN converges, but makes suboptimal decisions that are mainly focused on retrieving short-term reward

I use a dDQN to dispatch drivers in a ride-hailing environment. The action space has size (#drivers + 1), which means we can choose one of the drivers or choose to refuse an order (and wait for the ...
  • 3
2 votes
0 answers
34 views

How to fix high variance of the returns on a 2d env?

I'm trying to train an agent on a self-written 2d env, and it just doesn't converge to the solution. It is basically a 2d game where you have to move a small circle around the screen and try to avoid ...
2 votes
0 answers
122 views

Why does the number of input tokens to an LSTM have an impact on the convergence of Integrated Gradients?

Background I am computing the attribution scores for a simple LSTM model using Integrated Gradients. This method defines the contribution of a feature to a model prediction by integrating over the ...
  • 71
1 vote
1 answer
136 views

Is there a tutorial for understanding the proof of convergence for TD learning?

I'm reading the article An Analysis of Temporal-Difference Learning with Function Approximation (1997), but the mathematics inside seems overly complicated for me. Answers to some similar questions ...
1 vote
0 answers
59 views

Hand Landmark Detector Not Converging

I'm currently trying to train a custom model with TensorFlow to detect 17 landmarks/keypoints on each of 2 hands shown in an image (fingertips, first knuckles, bottom knuckles, wrist, and palm), for ...
2 votes
2 answers
298 views

How does $\alpha$ affect the convergence of the TD algorithm?

In Temporal-Difference Learning, we update our value function by $V\left(S_{t}\right) \leftarrow V\left(S_{t}\right)+\alpha\left(R_{t+1}+\gamma V\left(S_{t+1}\right)-V\left(S_{t}\right)\right)$ If we ...
  • 143
2 votes
0 answers
103 views

Why does TD (0) converge to the MLE solution of the Markov model?

Why does TD (0) converge to the MLE solution of the Markov model? Let's take the Example 6.4 in Sutton and Barto's book as an example. Example 6.4: You are the Predictor Place yourself now in the ...
  • 143
1 vote
0 answers
10 views

References for the convergence of gradient-based algorithms for training neural networks

I'm looking for some good references that give convergence results of training neural networks. I'm decently familiar with works that analyze the convergence of SGD, and, in particular, I really like ...
  • 976
3 votes
2 answers
2k views

How to check whether my loss function is convex or not?

Loss functions are useful in calculating loss and then we can update the weights of a neural network. The loss function is thus useful in training neural networks. Consider the following excerpt from ...
  • 3,251
1 vote
0 answers
33 views

Is there any work that applies the approach in "Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms" to standard Q-learning?

I am trying to mathematically characterize the finite sample convergence rates for Q-learning. To this end, I have read the following papers Learning rates for Q-learning, by Eyal Even-Dar et al.; ...
0 votes
0 answers
42 views

Why don't we use this intialization with SGD rather than random?

Suppose I have a loss function as a polynomial with its variables being the weights of a network I wish to tune. Now, we want to find the minima of the loss function - so basically ...
  • 126
4 votes
1 answer
115 views

Does elitism cause premature convergence in genetic algorithms?

I have a genetic algorithm which is working fairly well. It's got all the standard operators, including initial random population, crossover ratio, mutation rate, degree of mutation, etc. This works ...
5 votes
1 answer
549 views

Does the policy iteration convergence hold for finite-horizon MDP?

Most RL books (Sutton & Barto, Bertsekas, etc.) talk about policy iteration for infinite-horizon MDPs. Does the policy iteration convergence hold for finite-horizon MDP? If yes, how can we derive ...
5 votes
1 answer
361 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 ...
2 votes
1 answer
77 views

Why do I get the best policy before Q values converge using DQN?

I have implemented DQN algorithm and wonder why during testing, the best performance is achieved by a policy from about 300 episode, when mean Q values converge at about 800 episode? Mean Q-values ...
user avatar
1 vote
1 answer
89 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 ...
1 vote
0 answers
21 views

React on train-validation curve after trening

I have a regression task that I tray to solve with AI. I have around 6M rows with about 30 columns. (originally there was 100, but I reduce it with drop feature importance) I understand basic ...
1 vote
0 answers
53 views

How to have closer validation loss and training loss in training a CNN

I am using an AlexNet architecture as my Convolutional Neural Network. A learning rate of 0.00007 and 128 batch_size. I have 20000 data and 10% test, 40% validation, and 50% for training. I used 100 ...
  • 140
3 votes
1 answer
868 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
0 answers
121 views

Is Monte Carlo tree search guaranteed to converge to the optimal solution in two player zero-sum stochastic games?

I'm aware that convergence proofs for Monte Carlo tree search exist in the case of deterministic zero sum games and Markov decision processes. I have come across research which applies MCTS to zero-...
2 votes
1 answer
63 views

How much can an inclusion of the number of iterations have on the training of an MLP?

My doubt is like this : Suppose we have an MLP. In an MLP, as per the backprop algorithm (back-propagation algorithm), the correction applied to each weight is : $$ w_{ij} := -\eta\frac{\partial E}{\...
  • 185
4 votes
1 answer
818 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 ...
2 votes
0 answers
82 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 ...
  • 279
2 votes
0 answers
65 views

If the performance of an RL agent in a partially observable environment is "good", is this likely only accidental?

In my research, I remember to have read that, in case of an environment which can be modeled by partially observable MDP, there are no convergence guarantees (unfortunately, I do not find the paper ...
  • 291
7 votes
0 answers
216 views

Is the Bellman equation that uses sampling weighted by the Q values (instead of max) a contraction?

It is proved that the Bellman update is a contraction (1). Here is the Bellman update that is used for Q-Learning: $$Q_{t+1}(s, a) = Q_{t}(s, a) + \alpha*(r(s, a, s') + \gamma \max_{a^*} (Q_{t}(s', ...
2 votes
0 answers
624 views

Why is DDPG not learning and it does not converge?

I have used a different setting, but DDPG is not learning and it does not converge. I have used these codes 1,2, and 3 and I used different optimizers, activation functions, and learning rate but ...
2 votes
1 answer
68 views

What is convergence analysis, and why is it needed in reinforcement learning?

While reading a paper about Q-learning in network energy consumption, I came across the section on convergence analysis. Does anyone know what convergence analysis is, and why is convergence analysis ...
2 votes
0 answers
181 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? ...
1 vote
1 answer
404 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. ...
  • 291
3 votes
0 answers
86 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 ...
6 votes
1 answer
1k views

What are the conditions of convergence of temporal-difference learning?

In reinforcement learning, temporal difference seem to update the value function in each new iteration of experience absorbed from the environment. What would be the conditions for temporal-...
  • 163
2 votes
1 answer
905 views

Why isn't my implementation of A2C for the the atari pong game converging?

I have two different implementations with PyTorch of the Atari Pong game using A2C algorithm. Both implementations are similar, but some portion are different. https://colab.research.google.com/drive/...
  • 161
3 votes
0 answers
882 views

Why is it hard to prove the convergence of the deep Q-learning algorithm?

Why is it hard to prove the convergence of the DQN algorithm? We know that the tabular Q-learning algorithm converges to the optimal Q-values, and with a linear approximator convergence is proved. ...
3 votes
1 answer
677 views

Why do RL implementations converge on one action?

I have seen this happening in implementations of state-of-the-art RL algorithms where the model converges to a single action over time after multiple training iterations. Are there some general ...
1 vote
0 answers
85 views

When does Monte Carlo linear function approximation converge?

In this Stanford lecture (minute 35:47 and 37:00), the professor says that Monte Carlo (MC) linear function approximation does not always converge, and she gives an example. In general, when does MC ...
0 votes
1 answer
124 views

Is it a good idea to overfit on a small part of your data for faster model convergence?

I working on a classification problem that needs to detect patterns on a time serie. Basically, there's a catch-all class that means "no pattern detected", the other are for the specific patterns. The ...
  • 101
4 votes
1 answer
433 views

Neural network doesn't seem to converge with ReLU but it does with Sigmoid?

I'm not really sure if this is the sort of question to ask on here, since it is less of a general question about AI and more about the coding of it, however I thought it wouldn't fit on stack overflow....
4 votes
3 answers
523 views

Why can the Bellman equation be turned into an update rule?

In chapter 4.1 of Sutton's book, the Bellman equation is turned into an update rule by simply changing the indices of it. How is it mathematically justified? I didn't quite get the initiation of why ...
1 vote
1 answer
183 views

Why isn't the implementation of my policy evaluation for a simple MDP converging?

I am trying to code out a policy evaluation algorithm to find the $V^\pi(s)$ for all states. The following diagram below shows the MDP. In this case i let p = q = 0.5. the rewards for each states ...
  • 1,241
3 votes
1 answer
2k views

Is there an advantage in decaying $\epsilon$ during Q-Learning?

If the agent is following an $\epsilon$-greedy policy derived from Q, is there any advantage to decaying $\epsilon$ even though $\epsilon$ decay is not required for convergence?
  • 309
1 vote
0 answers
96 views

Does SARSA(0) converge to the optimal policy in expectation if the Robbins-Monro conditions are removed?

The conditions of convergence of SARSA(0) to the optimal policy are : The Robbins-Monro conditions above hold for $α_t$. Every state-action pair is visited infinitely often The policy is greedy with ...
  • 309