Questions tagged [convergence]
For questions related to the convergence of AI algorithms.
88
questions
0
votes
0
answers
7
views
FP32 with TF32 precision
I'm using PyTorch with V100 GPU. As this GPU doesn't support operations in TF32, I'm adjusting my x (input to the prediction model) and y (ground truth) tensors that are in FP32 to have 10-bit ...
- 1
2
votes
0
answers
50
views
Can Q-learning and other RL algorithms solve CNF SAT?
I encountered a question about solving CNF SAT using reinforcement learning: A state is a partial substitution to the variables, and each action is choosing an empty variable and set its value (to <...
- 121
0
votes
0
answers
26
views
Effectiveness of DNN training with reduced Batch randomness
So here's an example set to help explain my doubt. Suppose I have 80,000 total images available for a DNN training task. With a batch size of 32, that is 2500 batches.
Now let's say I partition the ...
0
votes
0
answers
61
views
Convergence of Value Iteration for Discount factor of 1
Given this pseudo code for value iteration:
In the case of gamma=1, under what conditions on the MDP will we still be able to find the optimal policy?
0
votes
0
answers
20
views
Are there are any truly chaotic systems in deep learning where convergence is not possible?
In the cases I have seen, neural networks have always converged (i.e., the loss function for the training data asymptotically approached some constant value). I have seen loss functions oscillate, ...
- 882
1
vote
1
answer
136
views
Why is policy iteration guaranteed to converge to the global optimum? [duplicate]
In reinforcement learning, what guarantees that policy iteration would find the globally optimal solution and not just any local maximum?
I'm reading the book "Reinforcement Learning: An ...
- 233
3
votes
1
answer
87
views
Prooving the convergence rate of estimators (machine Learning)
I want to estimate a quantity and have two choices for estimators (they both sample from the same distribution). I suspect one of them has a higher variance and thus a slower convergence rate. I want ...
1
vote
0
answers
42
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
64
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
484
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
136
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 ...
- 3,501
2
votes
1
answer
124
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
40
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
298
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
1
vote
2
answers
991
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 ...
- 113
0
votes
3
answers
95
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 ...
- 3,501
2
votes
0
answers
44
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 ...
- 21
2
votes
0
answers
144
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
229
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 ...
- 11
1
vote
0
answers
80
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 ...
- 111
2
votes
2
answers
548
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
147
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
12
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 ...
- 1,131
5
votes
2
answers
3k
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 ...
- 3,501
1
vote
0
answers
38
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
44
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
186
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 ...
- 149
5
votes
1
answer
706
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 ...
- 349
5
votes
1
answer
526
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 ...
- 215
2
votes
1
answer
89
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 ...
user43110
1
vote
1
answer
202
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 ...
- 687
1
vote
0
answers
23
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 ...
- 169
1
vote
0
answers
70
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
1k
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 ...
- 31
1
vote
0
answers
169
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-...
- 11
2
votes
1
answer
104
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 :
$$ w_{ij} := -\eta\frac{\partial E}{\...
- 185
4
votes
1
answer
1k
views
When do SARSA and Q-Learning converge to optimal Q values?
Here's another interesting multiple-choice question that puzzles me a bit.
In tabular MDPs, if using a decision policy that visits all states an infinite number of times, and in each state, randomly ...
- 1,081
2
votes
0
answers
152
views
How can deep Q-learning converge if the targets may not be correct?
In deep Q-learning, $Q(s, a)$ and $Q'(s, a)$ are predicted or estimated by the neural network itself. In supervised learning, the target value is a true unbiased value. However, this isn't the case in ...
- 329
2
votes
0
answers
71
views
If the performance of an RL agent in a partially observable environment is "good", is this likely only accidental?
In my research, I remember to have read that, in case of an environment which can be modeled by partially observable MDP, there are no convergence guarantees (unfortunately, I do not find the paper ...
- 311
7
votes
0
answers
238
views
Is the Bellman equation that uses sampling weighted by the Q values (instead of max) a contraction?
It is proved that the Bellman update is a contraction (1).
Here is the Bellman update that is used for Q-Learning:
$$Q_{t+1}(s, a) = Q_{t}(s, a) + \alpha*(r(s, a, s') + \gamma \max_{a^*} (Q_{t}(s',
...
- 71
2
votes
0
answers
788
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 ...
- 52
2
votes
1
answer
80
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 ...
- 21
2
votes
0
answers
222
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?
...
- 261
2
votes
1
answer
648
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. ...
- 311
3
votes
0
answers
103
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 ...
- 31
6
votes
1
answer
2k
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
1k
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
1k
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.
...
- 175
3
votes
1
answer
948
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
102
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 ...
- 852