My money is on this person thinking that each individual PS5 is running a live AI system for Sophy...which is laughable.Can I check what it is that you understand by this as, despite my own reinforcement, this seems to be a term you're relying on extensively.
Oooo ooo ooo Mr Famine Sir, I know I knowCan I check what it is that you understand by this as, despite my own reinforcement, this seems to be a term you're relying on extensively.
I'm trying to establish a baseline in order that we can converse on a common level - which, given the language differences, is kind of important - without wasting effort on misunderstandings but thanks for your assumptions and contribution 👍Well Famine, judging by the fact that you haven't actually contributed any information yourself, I can safely assume you know even less than they do. They're at least trying to explain how they think Sophy works, and you're just picking at a word and not addressing or contributing anything else.
This video explains it well:Can I check what it is that you understand by this as, despite my own reinforcement, this seems to be a term you're relying on extensively.
I'm sure it does, but I'm not looking for what other people think; I'm trying to determine what it is you understand by the term so that we have a common ground on which to converse - as previously stated:This video explains it well:
Can I check what it is that you understand by this as, despite my own reinforcement, this seems to be a term you're relying on extensively.
If you're just not interested in the discussion we can skip right past it I guess, but it's all a bit of a waste of everyone's time really.I'm trying to establish a baseline in order that we can converse on a common level - which, given the language differences, is kind of important - without wasting effort on misunderstandings
This video explains it well:
I think its kinda funny how people are only able to relate the idea to something they've already seen before as if its completely impossible for PD to incorporate an open world in any other way other than a way its already been done. "GTA"?!? Really????People, I'm not the only one that sees that "open world" means "no racing" and if it is "no racing" then it's not Gran Turismo.
Believe it or not, in the universe in which we occupy, two truths can exists in a singular space at the same time. It can be an open world where one could drive a car to a track and race said car, or even another car in a regulated race. You guys cannot be this unimaginative and/or open minded. "Old" aint no excuse, either.If you have proper, legitimate racing there needs to be restrictions of track, meaning you cannot go off track, cutting corners, choosing your own route bypassing the set track limits. If you have an open world environment you cannot have that legitimate race, it's basically that simple.
Thank you for pointing that out, I believed in the open world but when it came to racing it closed that openness.Believe it or not, in the universe in which we occupy, two truths can exists in a singular space at the same time. It can be an open world where one could drive a car to a track and race said car, or even another car in a regulated race. You guys cannot be this unimaginative and/or open minded. "Old" aint no excuse, either.
A neural network (or artificial neural network) is a computational model that consists of nodes and edges. There are input nodes, fed with data from sensors or with static values; output nodes, with control of various actions the AI can take, in the case of Sophy that includes braking and steering for example; and there are also one or more layers of hidden nodes.I'm sure it does, but I'm not looking for what other people think; I'm trying to determine what it is you understand by the term so that we have a common ground on which to converse - as previously stated:
If you're just not interested in the discussion we can skip right past it I guess, but it's all a bit of a waste of everyone's time really.
That's not quite how it works. You can't take a neural network and transform it into a set of instructions (if that's what you mean by "self contained model"). What we have on the PS5 is a neural network.The thing is, that Sophy is trained and then the behaviour packaged in to a self contained model on the console, it can’t learn from that point forward but it’s more than equipped to race and react to the pre described coding.
Machine learning is the process by which the neural network is trained. The neural network itself is not machine learning. The fact that Sophy uses a neural network to determine its actions does not imply that it's learning from what it's doing.Don’t confuse how you make Sophy with how you apply it to very tightly controlled domains.
I would leave that up to the players. Kind of like how there are lobbies dedicated to car shows, roleplaying ect. For instance imagine a freeway that goes around the entire menu/map. You and a friend can be meet at a designated point and race to another designated point. Maybe even implement waypoints. Yes, you're friend could cheat the whole way but, at that point, thats your fault for having a wack friend. jkjkThank you for pointing that out, I believed in the open world but when it came to racing it closed that openness.
I would love to have a point A to point B race but there would be many routes to take causing some restrictions. If you were even thinking to just cross-country it with an offload car it would cause more restrictions.
If there was a Cannonball type race there would be so many ways to cheat the system making it unfair to all except the cheaters.
Not fun, not racing.
Remember, GT is driving simulator, not racing, mkay?People, I'm not the only one that sees that "open world" means "no racing" and if it is "no racing" then it's not Gran Turismo.
Okay, I think I see where you're coming from now. We'll go with an "ehhhhhhhhhhhh fair enough, I guess".A neural network (or artificial neural network) is a computational model that consists of nodes and edges. There are input nodes, fed with data from sensors or with static values; output nodes, with control of various actions the AI can take, in the case of Sophy that includes braking and steering for example; and there are also one or more layers of hidden nodes.
In a feed-forward model, signals are passed from the input nodes to the first layer of hidden nodes. Each edge has a certain weight applied to it and if the sum of all incoming signals multiplied by their respective weights is greater than some threshold value, a signal from the hidden node is passed onto the next layer. Eventually the signals reach the output nodes and lead to some action taken by the agent.
The weights and thresholds are determined via the training process. The fact that you have a neural network does not mean it's learning from what it's doing. For it to learn anything you need to have a training algorithm, but that's not actually a part of the neural network.
That's not quite how it works. You can't take a neural network and transform it into a set of instructions (if that's what you mean by "self contained model"). What we have on the PS5 is a neural network.
You are right that it's doesn't learn anything from racing against you. The weights and thresholds are what they are. There's no technical limitation that prohibits it from learning though, the neural network that we have is of the same type as the one they use when training it. What's missing is a training algorithm, i.e. a function to reward or penalise Sophy based on its performance and a function to change the weights and thresholds. We are unlikely to ever get such an update though, because Sophy needs training at a massive scale to make significant improvements, so it makes no sense to train it on an individual level.
To be fair, there's only really a limited number of ways of doing it... ironically, I supposeI think its kinda funny how people are only able to relate the idea to something they've already seen before as if its completely impossible for PD to incorporate an open world in any other way other than a way its already been done. "GTA"?!? Really????
They use ML and then a little bit more ML but it has to be packaged.A neural network (or artificial neural network) is a computational model that consists of nodes and edges. There are input nodes, fed with data from sensors or with static values; output nodes, with control of various actions the AI can take, in the case of Sophy that includes braking and steering for example; and there are also one or more layers of hidden nodes.
In a feed-forward model, signals are passed from the input nodes to the first layer of hidden nodes. Each edge has a certain weight applied to it and if the sum of all incoming signals multiplied by their respective weights is greater than some threshold value, a signal from the hidden node is passed onto the next layer. Eventually the signals reach the output nodes and lead to some action taken by the agent.
The weights and thresholds are determined via the training process. The fact that you have a neural network does not mean it's learning from what it's doing. For it to learn anything you need to have a training algorithm, but that's not actually a part of the neural network.
That's not quite how it works. You can't take a neural network and transform it into a set of instructions (if that's what you mean by "self contained model"). What we have on the PS5 is a neural network.
You are right that it's doesn't learn anything from racing against you. The weights and thresholds are what they are. There's no technical limitation that prohibits it from learning though, the neural network that we have is of the same type as the one they use when training it. What's missing is a training algorithm, i.e. a function to reward or penalise Sophy based on its performance and a function to change the weights and thresholds. We are unlikely to ever get such an update though, because Sophy needs training at a massive scale to make significant improvements, so it makes no sense to train it on an individual level.
Machine learning is the process by which the neural network is trained. The neural network itself is not machine learning. The fact that Sophy uses a neural network to determine its actions does not imply that it's learning from what it's doing.
That package is the neural network. There's no other way to pack it.They use ML and then a little bit more ML but it has to be packaged.
I don't know what you mean by massive simulation machine, but it sounds like you might be confusing the infrastructure used to train the AI at a massive scale with the neural network itself.If you understand the project and the tech, it’s a massive simulation machine that just runs multiple simulated laps and inputs.
I don't understand what you mean by that.The tracks and cars are fixed variables so the pathing and tasking is easy to describe to the agents.
Sophy was trained from scratch, just like all neural networks have to be. You can't teach or instruct a neural network to do anything (at least not to any degree of success) without training it. I suppose that if your network is very small and the task you wish to perform is very simple you could make some educated guesses to what the weights and thresholds ought to be, but for those applications it would be easier, faster and better to just write an algorithm.This is not neural networks, it’s being able to simulate many agents to tune the optimum path, Sophy didn’t learn to drive, it already could it was used to find the optimum AI behaviour in a very very confined sandbox.
I don't know if there's a any OW racing game yet, that provides "serious" racing.Thank you for pointing that out, I believed in the open world but when it came to racing it closed that openness.
I would love to have a point A to point B race but there would be many routes to take causing some restrictions. If you were even thinking to just cross-country it with an offload car it would cause more restrictions.
If there was a Cannonball type race there would be so many ways to cheat the system making it unfair to all except the cheaters.
Not fun, not racing.
Damn man, you interrogated someone to prove they understand something, for what? Clearly not for the purpose of actually discussing it.Okay, I think I see where you're coming from now. We'll go with an "ehhhhhhhhhhhh fair enough, I guess".
Interrogated? Asked what they meant by certain terms, for the purposes of everyone understanding what they're talking about without jargon, in order that there's a common ground not mutated by language differences:Damn man, you interrogated someone to prove they understand something, for what? Clearly not for the purpose of actually discussing it.
Given that I already explained this, in the post quoted (and pooped upon), and that finding common ground is literally the point of discussion, it'd be nice if you could address why you think this is a Bad Thing that requires this sort of response.I'm trying to establish a baseline in order that we can converse on a common level - which, given the language differences, is kind of important - without wasting effort on misunderstandings
Beamng.drive. You just have to do the work yourself a lot of the time to create events.I don't know if there's a any OW racing game yet, that provides "serious" racing.
Given that I already explained this, in the post quoted (and pooped upon), and that finding common ground is literally the point of discussion, it'd be nice if you could address why you think this is a Bad Thing that requires this sort of response.
Where's the actual discussion on the topic? It's not like you were already discussing Sophy AI and there was some misunderstanding that needed to be sorted out. "A common ground on which to converse"... where was the conversing after they showed that they understood the topic? You were testing someone on their knowledge, and that was the whole discussion, because you dropped it afterwards.I'm sure it does, but I'm not looking for what other people think; I'm trying to determine what it is you understand by the term so that we have a common ground on which to converse - as previously stated:
If you're just not interested in the discussion we can skip right past it I guess, but it's all a bit of a waste of everyone's time really.
In intervening posts - and you'll notice that some other members were also wondering quite what he meant and were confused by it. After @eran0004 clarified, we're now all at a common place, and there is an ongoing discussion between him and @newmedia_dev on the subject.Where's the actual discussion on the topic?
No, I was asking what they meant by the terms they used (which are often misused terms) to clarify what they were saying.You were testing someone on their knowledge, and that was the whole discussion, because you dropped it afterwards.
Someone posting in English is not necessarily comprehending the same terms in the same way if they are not English - particularly if they are technical terms or jargon. We even see this with British English and US English, never mind someone who is and presents as Swedish (which has a high level of English literacy).Also, every message they posted was perfectly fluent English, so that reasoning is a bit weird when there was just no indication of a language barrier at all.
You are welcome to read whatever you want in any manner you desire, but currently you're having a go at me for trying to make sure everyone's speaking about the same thing to keep the discussion at a sensible level without pointless arguments caused by misunderstanding, over someone who had no problem with it whatsoever and clarified their comments without complaint*.If you genuinely want to know, it just comes across as petty and rude, even if that wasn't your intention.
Being more grounded, the reason we know this isn't happening for anything more than a moon mission/music rally style side thing is Sophy.
You don't invest half a decade and very sizeable electricity costs (training LLMs isn't cheap!) into developing a state-of-the-art closed ciruit racing AI, just for your next game to not be primarily a closed circuit racer.