AI bots trained for 180 years a day to beat humans at Dota 2
1–10 of 14 posts
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#2>>On one hand, this is a testament to the power of contemporary machine learning methods and the latest computer chips to process vast amounts of data. On the other, it’s a reminder of how fundamentally unintelligent AI agents are.
forgive any ignorance, but how do changes to the game affect AI behavior? E.g. New characters, new maps, balance changes, bug fixes, etc. Do the AI have to be re-trained in a similar amount time, or is it expedited? How adaptive are the A.I. systems?
What I'm getting at is - in a real world scenario (like the city transportation example from the article), how quickly can the A.I. respond to things unexpected changes (natural disasters, accidents, etc)? Will they be able to handle the unexpected in a safe time frame?
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#3A great achievement even for a game which is relatively simplistic like a MOBA. Still waiting for AI to become competitive in Starcraft which i think is a much greater challenge.
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#4>>On one hand, this is a testament to the power of contemporary machine learning methods and the latest computer chips to process vast amounts of data. On the other, it’s a reminder of how fundamentally unintelligent AI agents are. forgive any ignorance, but how do changes to the game affect AI behavior? E.g. New characters, new maps, balance changes, bug fixes, etc. Do the AI have to be re-trained in a similar amoun…
Depends on the program, of course. You're asking how robust the trained model is to outliers and how effective it is at extrapolation. Different training algorithms have different behaviors.
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#5>>On one hand, this is a testament to the power of contemporary machine learning methods and the latest computer chips to process vast amounts of data. On the other, it’s a reminder of how fundamentally unintelligent AI agents are. forgive any ignorance, but how do changes to the game affect AI behavior? E.g. New characters, new maps, balance changes, bug fixes, etc. Do the AI have to be re-trained in a similar amoun…
A Reinforcement Learning machine would have to be re-trained for changes such as that, but not from scratch. Depending on the size of the change, it would take much less time to adapt to such a change.
Several notes:
-The article notes that a lot of the hard parts of human video-game playing have been done 'for' the AI by hardcoding. It doesn't actually have to look at the screen to parse information--it has direct access to game variables that player would have to access through menus. More relevant to your question, a lot of the strategic decisions like item purchasing, ward placement, and probably character placement were just picked by the programmers or set to be ignored. The whole thing is less impressive than the headline sounds. I think it was just learning--where to run on the map and when to attack things?
-RL is based on deep learning, and there are fundamental issues with deep learning's ability to adapt to genuinely new scenarios. None of these system can presently adapt to something genuinely unprecendeted in a time frame you would consider 'safe'. They need at least several opportunities to observe how the world works after the changes and the consequences of their actions. To try to make this concrete--they can't reason about what implications a flood/power outage/landslide has for their traffic management. They can only learn from trial and error <-(the important part) how traffic behaves during a disaster.
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#6Somewhat misleading title: they're playing a restricted set of DotA 2 (only 5 heroes instead of 100+, some mechanics turned off), and some important decisions are handled by hard-coded rules rather than the main AI.
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#7>>On one hand, this is a testament to the power of contemporary machine learning methods and the latest computer chips to process vast amounts of data. On the other, it’s a reminder of how fundamentally unintelligent AI agents are. forgive any ignorance, but how do changes to the game affect AI behavior? E.g. New characters, new maps, balance changes, bug fixes, etc. Do the AI have to be re-trained in a similar amoun…
A Reinforcement Learning machine would have to be re-trained for changes such as that, but not from scratch. Depending on the size of the change, it would take much less time to adapt to such a change. Several notes: -The article notes that a lot of the hard parts of human video-game playing have been done 'for' the AI by hardcoding. It doesn't actually have to look at the screen to parse information--it has direct a…
> RL is based on deep learning
False. Reinforcement Learning is a category of algorithm. There are many possible implementations, not only "deep learning". Further, you might be surprised at how well a generalized, trained model might mimic "reasoning".
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#8A great achievement even for a game which is relatively simplistic like a MOBA. Still waiting for AI to become competitive in Starcraft which i think is a much greater challenge.
An impossible to beat Starcraft AI is already doable without all this AI training. Just by controlling every individual unit seperatly in impossible to counter maneuvers far beyond any human actions per minute.
You could basically get an AI to win every single time with a handful of zerglings in a few minutes this way.
You could train an AI for 1 billion years a day to play pong or you could hardcode it to never miss the ball.
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#9A great achievement even for a game which is relatively simplistic like a MOBA. Still waiting for AI to become competitive in Starcraft which i think is a much greater challenge.
I've played both games extensively and imho calling dota simplistic is not fair.
Re: AI bots trained for 180 years a day to beat humans at Dota 2
#10A great achievement even for a game which is relatively simplistic like a MOBA. Still waiting for AI to become competitive in Starcraft which i think is a much greater challenge.
An impossible to beat Starcraft AI is already doable without all this AI training. Just by controlling every individual unit seperatly in impossible to counter maneuvers far beyond any human actions per minute. You could basically get an AI to win every single time with a handful of zerglings in a few minutes this way. You could train an AI for 1 billion years a day to play pong or you could hardcode it to never miss…
Are you sure? i.e. has this been proven on pro level SC players?
I think a smart player could know the player was going Zerg, and wall in.. and make some decisions that make the micro of Zerg less useful.