Neil Slater
  • Member for 5 years, 4 months
  • Last seen this week
  • Durham, United Kingdom
Additional (Potential) Action for Agent in MazeGrid Environment (Reinforcement Learning)
Accepted answer
0 votes

You can definitely define an environment that accepts more types of action, including actions that take multiple steps in a direction. The first thing you would need to do is implement support for ...

View answer
In vanilla policy gradient is the baseline lagging behind the policy?
Accepted answer
0 votes

So is the baseline expected to be used in the next iteration when our policy has changed? Yes. To compute the advantage we subtract the state value $V(s_{t})$ from the action value $Q(s_{t},a_{t})$...

View answer
Is there 1-dimensional reinforcement learning?
Accepted answer
0 votes

From what I can find, reinforcement algorithms work on a grid or 2-dimensional environment. A lot of teaching materials use a "grid world" presentation to demonstrate basic reinforcement learning (RL)...

View answer
How do you know if an agent has learnt its environment in reinforcement learning?
Accepted answer
0 votes

This depends on the complexity of the environment being learned, and the purpose for learning it. There is no general answer. For the simple environments used to teach reinforcement learning (RL), ...

View answer
Adversarial Q Learning should use the same Q Table?
0 votes

should I let both 'players' use, and update, the same Q Table? Yes this works well for zero-sum games, when player 1 wants to maximise a result (often just +1 for "player 1 wins") and player 2 wants ...

View answer
Reinforcement Learning (and specifically REINFORCE algorithm) for one-round "games"
0 votes

You should look into contextual bandits, and specifically gradient bandit solvers (see section 13). Your derivation of the gradient seems correct to me. Instead of a sampled/bootstrapped value ...

View answer
How to estimate a behavior policy for off-policy learning based on data?
Accepted answer
0 votes

Is there a way to estimate a behavior policy from this dataset so that it can be used in an off-policy learning algorithm? If you have enough examples of $(s,a)$ pairs for each instance of $s$ then ...

View answer
Can this be a possible deep q learning pseudocode?
Accepted answer
0 votes

It looks generally valid to me. There are a couple of things missing/implied that I'd like to give feedback on though: I am not using replay here Then it won't work, except for the most simple and ...

View answer
Recurrent Neural Network to track distance from origin
Accepted answer
0 votes

This kind of problem does not really have a name other than "toy problem" since no-one needs to teach an AI to add up, multiply or divide* - there are already far more reliable and far faster ways to ...

View answer
Can a model, retrained on images classified previously by itself, increase its accuracy?
Accepted answer
0 votes

The most likely outcome of this approach is wasted time and very little effect on accuracy. There will be changes to the model. Some will be beneficial and improve the model, but some will backfire ...

View answer
Training Keras Towards Or Against Analog Value?
Accepted answer
0 votes

What is the technical name for this kind of training? The name for the problem is Sequential Decision Making or Optimal Control. There are a few different approaches you can take when solving this ...

View answer
Can an RL algorithm trained in one environment be successful in a different one?
Accepted answer
0 votes

Can an RL algorithm trained in one environment be succesfull on a different one? Strictly the answer here is "no". You train an agent to solve a single environment. If a second environment is ...

View answer
How can I train a neural network to give probability of a random event?
0 votes

This approach: train it as a classification problem which output confidence, and hope that the confidence will reflect the actual probability. Sometimes the network would output the correct ...

View answer
Can the inputs and outputs of a neural network be a neural network?
Accepted answer
0 votes

A neural network essentially is a function: $$\mathbf{y} = f(\mathbf{x}, \mathbf{\theta})$$ Where $\mathbf{x}$ is a vector input, $\mathbf{\theta}$ are changeable or learnable parameters, and $\...

View answer
What is the reason behind using a test batch size?
Accepted answer
0 votes

I am not familiar with using batches during network evaluation. Can someone explain what is the reason behind using it and what are advantages and disadvantages? It is usually just for memory use ...

View answer
Some RL algorithms (especially policy gradients) initialize with random policies, which often manifests as random jitter on spot for a long time?
Accepted answer
0 votes

Where can I find sources showing that policy gradients initialize with random policies, whereas Q-Learning uses epsilon-greedy policies? You can find example algorithms for Q learning and policy ...

View answer
Why do we need floats for using neural networks?
0 votes

It is possible in principle, but you will end up emulating floating point arithmetic using integers in multiple places, so it is unlikely to be efficient for general use. Training is likely to be an ...

View answer
How is the constraint $\|f(x)\|_{2}=1$ enforced for the embedding $f(x)$ in the FaceNet paper?
Accepted answer
0 votes

The constraint is enforced with bespoke code. If FaceNet was implemented in NumPy, and the embedding layer vector (pre-constraint) was in the NumPy array h, then the code might look like: e = h / np....

View answer
Could a CNN hear the difference between sound of a pet moving, and a person?
Accepted answer
0 votes

I think it should be possible. The main difficulty will be in getting enough labelled data, deep learning approaches are very data hungry. Audio tasks such as speech typically require hours of ...

View answer
1
16 17 18 19
20