So, it's basically working as a goal-oriented fuzzer.
Fuzzers are like bug/anomaly/new state finding-oriented reinforcement learning programs, so yeah, in a way :P
AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
11–20 of 47 posts
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#12Well how do you say what's cheating or not? It works and it increases the evaluation score In this case one possible workaround to "cheating" would be to reduce the control precision, add some jittering to control inputs or change the goal function. But I'd say if it's being done solely with using the intended controls it's not cheating (as opposed to changing memory or using a debug 'cheat code'). Still, even in rea…
If it’s not technically cheating, it could be described as gamesmanship.
From Wikipedia https://en.m.wikipedia.org/wiki/Gamesmanship
“Gamesmanship is the use of dubious (although not technically illegal) methods to win or gain a serious advantage in a game or sport. It has been described as "Pushing the rules to the limit without getting caught, using whatever dubious methods possible to achieve the desired end".”
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#13This reminds me of AI research using NES Games. The AI eventually became proficient at completing Mario levels, and along the way it discovered novel strategies for survival, obtaining points, and finishing levels. > Check out this timestamp to watch the machine "cheat": https://youtu.be/xOCurBYI_gY?t=9m55s > Researcher's site about the project: http://www.cs.cmu.edu/~tom7/mario/ > The Paper: The First Level of Super…
This guy. One of my favorite YouTube channels. Releases something like once a year but oh boy, worth the wait. Check it out if you're a nerd and like creative/useless stuff. ;)
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#14The title seems misleading to me. The AI isn't finding bugs by somehow examining the game's source code, it's trying random gameplay and exploiting any advantages that emerge. That it's finding previously unknown bugs seems to be almost entirely down to trying things that human players wouldn't think to do.
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#15Well how do you say what's cheating or not? It works and it increases the evaluation score In this case one possible workaround to "cheating" would be to reduce the control precision, add some jittering to control inputs or change the goal function. But I'd say if it's being done solely with using the intended controls it's not cheating (as opposed to changing memory or using a debug 'cheat code'). Still, even in rea…
It isn't cheating - as far as the program is concerned, each bug is another rule.
To understand the concept of cheating, and to discuss what is cheating, requires an entirely higher cognitive capability.
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#16The title seems misleading to me. The AI isn't finding bugs by somehow examining the game's source code, it's trying random gameplay and exploiting any advantages that emerge. That it's finding previously unknown bugs seems to be almost entirely down to trying things that human players wouldn't think to do.
I haven't read the article yet, and I was not mislead by the title. I guess it helps to be familiar with the way reinforcement learning agents are hooked up to a simulation environment.
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#17The title seems misleading to me. The AI isn't finding bugs by somehow examining the game's source code, it's trying random gameplay and exploiting any advantages that emerge. That it's finding previously unknown bugs seems to be almost entirely down to trying things that human players wouldn't think to do.
You confuse bug (unintended behavior) with its cause (bad code).
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#18The title seems misleading to me. The AI isn't finding bugs by somehow examining the game's source code, it's trying random gameplay and exploiting any advantages that emerge. That it's finding previously unknown bugs seems to be almost entirely down to trying things that human players wouldn't think to do.
The AI isn't finding bugs by somehow examining the game's source code
The title doesn't say that.
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#19Well how do you say what's cheating or not? It works and it increases the evaluation score In this case one possible workaround to "cheating" would be to reduce the control precision, add some jittering to control inputs or change the goal function. But I'd say if it's being done solely with using the intended controls it's not cheating (as opposed to changing memory or using a debug 'cheat code'). Still, even in rea…
If it’s not technically cheating, it could be described as gamesmanship. From Wikipedia https://en.m.wikipedia.org/wiki/Gamesmanship “Gamesmanship is the use of dubious (although not technically illegal) methods to win or gain a serious advantage in a game or sport. It has been described as "Pushing the rules to the limit without getting caught, using whatever dubious methods possible to achieve the desired end".”
Another term for this is "angle shooting".
Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
#20Can we put AI to work on proving that we live in a simulation? I would never enter/exit my apartment 38 times alternating between forwards, backwards and each side, but an AI would. Maybe then all the walls start flashing and then we'll know!