Questions tagged [decision-theory]
For various clarifications/proofs behind an Artificially Intelligent agent's reasoning process using Decision Theory.
22
questions
1
vote
1
answer
87
views
How to prove that an action-value function optimal for one problem formulation is also optimal for another?
I want to ask about the intuition/where-to-look/what-to-try if I want to prove that an action value function optimal for a problem is also optimal for another reformulation of that smae problem. For ...
CommunityBot
- 1
0
votes
0
answers
39
views
Optimal decision with continuous, stochastic signals and rewards
I am performing a task, where I have to decide which projects to pursue at a given point in time, where the projects have different horizons of 30 minutes.
At a given point in time, forecasts are made ...
- 1
0
votes
0
answers
15
views
Do Bernoulli bandits need a different treatment if the rewards are sparse?
I have a problem where, effectively, my slot machines have very low payout probability (on the order of 1% for the "best" slot machines) and my goal is to minimize the number of actions to ...
- 1,349
182
votes
12
answers
60k
views
Could a paradox kill an AI?
In Portal 2 we see that AI's can be "killed" by thinking about a paradox.
I assume this works by forcing the AI into an infinite loop which would essentially "freeze" the computer's consciousness.
...
- 3,840
1
vote
0
answers
26
views
Can you correlate decision boundary of final layer of a neural network to predictive distribution?
I was reading in a On the Decision Boundary of Deep Neural Networks
that the final layer of a MLP can be equated to an SVM and can generate decision boundaries similar to methods with SVM. I was ...
- 797
1
vote
1
answer
118
views
Why is the entire area of a join probability distribution considered when it comes to calculating misclassification?
In the image given below, I do not understand a few things
1) Why is an entire area colored to signify misclassification? For the given decision boundary, only the points between $x_0$ and the ...
CommunityBot
- 1
104
votes
14
answers
8k
views
How could self-driving cars make ethical decisions about who to kill?
Obviously, self-driving cars aren't perfect, so imagine that the Google car (as an example) got into a difficult situation.
Here are a few examples of unfortunate situations caused by a set of events:
...
1
vote
1
answer
421
views
Can optimizing for immediate reward result in a policy maximizing the return?
The goal of a reinforcement learning agent is to maximize the expected return which is often a discounted sum of future rewards. The return indeed is a very noisy random variable as future rewards ...
- 32.1k
20
votes
1
answer
1k
views
Would Google's self-driving-car stop when it sees somebody with a T-shirt with a stop sign printed on it?
In Hidden Obstacles for Google’s Self-Driving Cars article we can read that:
Google’s cars can detect and respond to stop signs that aren’t on its map, a feature that was introduced to deal with ...
CommunityBot
- 1
1
vote
1
answer
93
views
Help with Novelty Recognition and Binary Classification for Emotion Recognition
I’m looking for advice regarding my ML project.
Using a special wristband, I am able to collect a bunch of physiological data from human subjects. I want to develop an application to recognize when ...
- 7,503
1
vote
1
answer
3k
views
Getting Negative Information Gain (using Entropy as a measure of disorder)
I'm creating a Decision Tree and at the very root level itself, I'm getting negative Information Gain.
As per my knowledge, Information Gain is always > 0....
...
CommunityBot
- 1
2
votes
1
answer
93
views
Should I use Monte Carlo or a classifier for this Decision Making problem?
I want to build a model to support decision making for loan insurance proposal.
There are three actors in the problem: a bank, a loaner applicant (someone who ask for a loan) and a counselor. The ...
- 10.3k
2
votes
1
answer
219
views
Is there any flaw to this solution to the One shot prisoner's dilemma
I wrote a solution to the one shot Prisoner's dilemma:
Introduction
My solution applies to a prisoner dilemma involving two people (I have neither sufficient knowledge of the prisoner'...
- 9,267
8
votes
1
answer
163
views
Zilberstein's "LP-dominate" pruning explained?
How does in the (famous Zilberstein) PR(uning) algorithm below the LP-dominate function get started: the first time it's called, ...
CommunityBot
- 1
2
votes
1
answer
116
views
Is there a name for this principle?
I have an idea for a transformative decision rule (TDR), but I want to know if there's already a name for it.
Any ordinal scale should be converted to a scale such that all the outcomes are ...
CommunityBot
- 1
1
vote
0
answers
64
views
What is the state of the art in models of how the human brain performs goal-directed decision making? Can these models' principles be applied to AI?
What is the state of the art in models of how the human brain performs goal-directed decision making? Can these models’ principles and insights be applied to the field of Artificial Intelligence, e.g. ...
CommunityBot
- 1
1
vote
0
answers
56
views
Condition Action Statement - Feed Forward Neural Network
I am trying to produce Decision Tree from Feed Forward Neural Network .
The input to the feed forward neural network is Condition Action Statement
for example, if airthrusthold > 90 , power up the ...
- 111
4
votes
2
answers
511
views
How to define or represent evil in logic
Is there any well defined method to define or represent evil in abstract logic, binary or AI form?
Video games method of representing evil is relative to the player context (thus subjective, and not ...
CommunityBot
- 1
3
votes
2
answers
142
views
Making decision based on users' reports
I have users' reports about an accident. I want to know how to make sure that the number of reports is big enough to take that accident as a true accident and not spam.
My idea is to consider a ...
CommunityBot
- 1
2
votes
1
answer
435
views
What would happen if someone jumped in the front of a Google car?
The Situation:
A self-driving car is traveling at it's maximum speed, 25 mph (40 km/h), in the middle of an empty street with the ability to change lanes on both sides. There are two passengers, one ...
- 136
4
votes
1
answer
751
views
How to represent a large decision tree?
A system makes a decision basing on a large number of varied factors, following a "live" decision tree - one that is (independently, through other subsystem) updated with new decisions, new situations....
- 1,945
4
votes
2
answers
141
views
Is it ethical to implement self-defence for street walking AI robots?
Would it be ethical to implement AI for self-defence for public walking robots which are exposed to dangers such as violence and crime such as robbery (of parts), damage or abduction?
What would be ...
- 2,599