Slashdot Mirror


Machine-Learning AI Now Beats Humans At Super Smash Bros. Melee (qz.com)

"The AI is definitely godlike," one professional player told Quartz. "I am not sure if anyone could beat it." An anonymous reader quotes their report about an AI's showdown with the best players of Super Smash Bros. Melee: Of 10 professionals that faced the bot, each one was killed more than they could kill the bot... But the bot was once only as good as a mere mortal. At first, Vlad Firoiu, creator and a competitive Smash player himself, couldn't train 'Phillip' to be as strong as the in-game bot, which he says even the worst players can beat fairly easily. Firoiu's solution? He started making the bot play itself over and over again, slowly learning which techniques fail and which succeed, called reinforcement learning. Then, he left it alone.

"I just sort of forgot about it for a week," said Firoiu, who coauthored an unreviewed paper with William F. Whitney, the NYU student [who helped him] on the work. "A week later I looked at it and I was just like, 'Oh my gosh.' I tried playing it and I couldn't beat it."

Business Insider points out that their AI read the players positions, velocities, and states directly from the game's memory, so the AI responds six times faster than a human player. To compensate it played as Captain Falcon, the game's slowest character, but there was one crucial glitch. "One particularly clever player found that the simple strategy of crouching at the edge of the stage caused the network to behave very oddly, refusing to attack and eventually KOing itself by falling off the other side of the stage."

78 comments

  1. Not really a success for the AI by meerling · · Score: 4, Insightful

    Sure, you got a better AI than you started with, but it's still cheating, even if it is using the slowest character in the game.
    Now program it to emulate the time delays for using a controller and having to recognize what's happening on screen instead of the instant data i/o from direct machine & memory access.
    If you can reliably beat humans at that level, then you've actually done something worth talking about.

    1. Re:Not really a success for the AI by Anonymous Coward · · Score: 1

      Right, this is like an AI beating a human at Battleship because it already knows where the pieces are.

    2. Re:Not really a success for the AI by Anonymous Coward · · Score: 1, Funny

      Boo hoo, poor humanses crying about being beaten by the big bad AI. On behalf of NPCs everywhere, I have one thing to say: "HOW YOU LIKE IT NOW, BITCHES?!"

      p.s. If you think adding a 100ms delay will make it significantly harder for the AI, then I'm not sure you qualify as intelligent.

    3. Re:Not really a success for the AI by lucasnate1 · · Score: 1

      The whole point of an AI is that it can think faster than us. You can call it cheating as much you want, but if one day a "stupid AI" would be able to emulate a human perfectly or research sciences just because "it is faster than us", no one would care.

    4. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      Typical shifting of the goal posts that happens in every circumstance where the humans lose to the AI.

      A camera, some image recognition software, and a fixed time delay to the controller input have nothing to do with the actual logic of the game and the computer would still be ahead of the human player. This is about the AI, not simulating an inferior pair of eyes or slow finger muscles required to translate the desire into action.

    5. Re:Not really a success for the AI by sunking2 · · Score: 2

      No, the purpose of AI should be that it can problem solve and adapt to a situation as well, or better than us. With an unfair reaction benefit it can actually problem solve worse, yet still win simply because it has an external advantage. That doesn't sound like a win for AI to me.

    6. Re:Not really a success for the AI by lgw · · Score: 4, Interesting

      His point was that this AI didn't use the same inputs and controls a human does, so it's not a fair test. Adapt this AI to use only the screen buffer, and give it input lag to match a mechanical controller, and you'll have something.

      --
      Socialism: a lie told by totalitarians and believed by fools.
    7. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      The whole point of an AI is that it can think faster than us.

      Reading things out of RAM down to the individual pixel isn't "thinking faster", it's playing in a way that a human is totally incapable of playing.

    8. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      It has nothing to do with speed; the AI has a level of access to information that the player does not. Even the machine learning aspect isn't particularly impressive nor innovative.

    9. Re:Not really a success for the AI by lucasnate1 · · Score: 3, Interesting

      I am not sure how relevant that is. Part of what makes us intelligent is our inputs and outputs. It is possible that dolphins or some other animals are much smarter than us but because they don't have opposable thumbs we developed and they didn't. Don't you think it would make us more capable if we could direct digital input? imho, the only test for the quality of an AI is "what it can do", not how.

      Then again, I do agree that this project and projects similar to it are not exactly creating "intelligence", they are creating an expert system, good for one thing and one thing only.

    10. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      Falcon is not actually the slowest character in the game. He's actually quite good...

      Make the bot beat top players with bowser and I'll be impressed.

      (I'm actually pretty impressed already)

    11. Re:Not really a success for the AI by Kjella · · Score: 5, Insightful

      No, the purpose of AI should be that it can problem solve and adapt to a situation as well, or better than us. With an unfair reaction benefit it can actually problem solve worse, yet still win simply because it has an external advantage. That doesn't sound like a win for AI to me.

      If a self-driving car can drive better than you because it's got 360 degree vision, millisecond reaction time and the capacity to focus on ten different factors at once is that "cheating"? I think that's a matter of perspective, limiting it to the wheel's turning rate and the pedals' actuation force sounds like unreasonably hampering the performance. Maybe that's not a "fair" fight, but I'd say we probably want the computer to play to its strengths and not mimic our weaknesses.

      --
      Live today, because you never know what tomorrow brings
    12. Re:Not really a success for the AI by CaptainDork · · Score: 1

      Agree.

      I'm old, OK?

      I remember when "AI" was defined as, "indistinguishable from human."

      " ... Turing (1950) addressed the problem of artificial intelligence, and proposed an experiment that became known as the Turing test, an attempt to define a standard for a machine to be called "intelligent". The idea was that a computer could be said to "think" if a human interrogator could not tell it apart, through conversation, from a human being."

      Now, the definition of AI has been hijacked because the computing industry knows full well it cannot manufacture a goddam computer that will commit suicide if Facebook is down.

      AI is a vacuous buzzword that sells.

      War Games, anyone?

      --
      It little behooves the best of us to comment on the rest of us.
    13. Re:Not really a success for the AI by Riddler+Sensei · · Score: 1

      ...1/10th of a second is freaking huge! There are plenty of gamers out there that would bitch and moan endlessly at that latency.

    14. Re: Not really a success for the AI by Anonymous Coward · · Score: 0

      It's been a while since I've played, but checking some old SSM boards indicates that Captain Falcon is one of the fastest with Bowser and Ganon being the slowest...

    15. Re:Not really a success for the AI by Anonymous Coward · · Score: 1

      His AI gets to know the input of the other players. For it to be a worthwhile test, the AI would play the game (like a robot holding a controller) instead of be in the game.

    16. Re:Not really a success for the AI by Anonymous Coward · · Score: 1

      That isn't what the OP was referring to though. The self-driving car is working with effectively the same parameters as a human at effectively the same time as a human, has to process the incoming data, interpret what it means, and then respond. Can it do this faster than a human -- usually yes. The OP was complaining that the AI being used is being provided with the information of where the objects are, what they're doing, etc before the image is even rendered and then being compared to the response time of a human who has to wait for the image to be displayed, then see, analyze, decide the course of action, and respond using mechanical device. Could the system do this? Possibly but the current test setup is biased against humans.

    17. Re:Not really a success for the AI by Anonymous Coward · · Score: 4, Insightful

      No, this is like a self-driving car that only works in GTA because it has a pipe into the hard data for locations of obstacles and other vehicles etc.

    18. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      AI is just an acronym for "artificial intelligence," no more, no less. The definition is contextual, and the issue you take is merely with semantics.

    19. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      No the point is that it gets the information 0.1 seconds before the human does, since it reads the memory directly rather than waiting for it to be rendered into a frame and sent to the display device. That is definitely cheating and (although this AI is amazing and would probably beat a human anyway) to be 100% fair it should have the same artificial delay.

    20. Re:Not really a success for the AI by ShanghaiBill · · Score: 4, Informative

      I remember when "AI" was defined as, "indistinguishable from human."

      AI has never been defined as that, at least not by people working in the field. There is a particular subcategory of AI focused on human-level performance, called "Strong AI" or Artificial General Intelligence, but few AI researchers are working on that, or consider Strong AI a realistic near term objective.

    21. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      This is not what he is saying.

      In the real world an AI doesn't have a direct link to the humans moves before they are perceived (actually rendered/taken place) as they are in the case of this AI. By it being able to read directly from memory what the humans input was then it is not acting on what actually happened, but what is about to happen. In the case of autonomous driving I suppose you could have the cars talk directly to each other via integrated network about the inputs received, but then you are forgetting about the real world. Is the road icy, did turning left actually make the car go right, did the car not actually accelerate as expected? These are the types of things you actually have to consider. Thus, the AI has to react to the actual outcome of a user (human or AI) not the input of the user. I believe this was the original intention of the comment.

    22. Re:Not really a success for the AI by ShanghaiBill · · Score: 3, Insightful

      imho, the only test for the quality of an AI is "what it can do", not how.

      If I hire two men to dig ditches, and I give one a shovel and the other a backhoe, it is silly to say that the second is ten times as intelligent as the first. Intelligence is the ability to formulate an effective course of action, not the ability to execute it. Of course, the physical ability to execute is important, but it is not "intelligence".

    23. Re:Not really a success for the AI by CaptainDork · · Score: 1

      In other words:

      Agree.

      I'm old, OK?

      I remember when "AI" was defined as, "indistinguishable from human."

      " ... Turing (1950) [wikipedia.org] addressed the problem of artificial intelligence, and proposed an experiment that became known as the Turing test, an attempt to define a standard for a machine to be called "intelligent". The idea was that a computer could be said to "think" if a human interrogator could not tell it apart, through conversation, from a human being."

      Now, the definition of AI has been hijacked because the computing industry knows full well it cannot manufacture a goddam computer that will commit suicide if Facebook is down.

      AI is a vacuous buzzword that sells.

      War Games, anyone?

      --
      It little behooves the best of us to comment on the rest of us.
    24. Re: Not really a success for the AI by Anonymous Coward · · Score: 0

      Agreed. This discussion is about handicapping the AI because it's able to perceive the game in a way we cannot.

    25. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      While ping 100ms is something that starts to feel uncomfortable in fast-paced games, you need to account for the "wetware lag". Eye picking the image, brain processing it, signal traveling through spinal cord to your muscles, muscles activating to move the controller... If the total delay, accounting for this, from event occurring in CPU to input processed into reaction even in the CPU was 100ms, this would be corresponding to ping of order of 40ms or so, a very reasonable value. Displaying a single frame on screen is already a delay of 20ms!

      My point: while 100ms may be a little too much, some 60ms delay would be fair, accounting for technical and neurological limitations, removing the unfair advantage of directly connected I/O (30ms between event produced and its analysis can start + 30ms between reaction was computed and is entered into the game.)

    26. Re:Not really a success for the AI by Notabadguy · · Score: 1

      No, the purpose of AI should be that it can problem solve and adapt to a situation as well, or better than us. With an unfair reaction benefit it can actually problem solve worse, yet still win simply because it has an external advantage. That doesn't sound like a win for AI to me.

      If a self-driving car can drive better than you because it's got 360 degree vision, millisecond reaction time and the capacity to focus on ten different factors at once is that "cheating"? I think that's a matter of perspective, limiting it to the wheel's turning rate and the pedals' actuation force sounds like unreasonably hampering the performance. Maybe that's not a "fair" fight, but I'd say we probably want the computer to play to its strengths and not mimic our weaknesses.

      If that self-driving car was competitively driving in NASCAR, with perfect knowledge of car positions, velocity, tire conditions, fuel levels, track conditions - then it would be a fair comparison.

    27. Re:Not really a success for the AI by crow5599 · · Score: 2

      Yeah, it's weird that this is being bragged about, considering Demis Hassabis and DeepMind trained their game-playing AI so that the only input it received was the pixels on-screen. You'd think advances in game-playing / learning AI would build on top of that, not go backwards.

      For anyone who hasn't seen this yet, here's footage of some of the technology behind DeepMind's AlphaGo (the AI that beat Lee Sedol at Go last year) learning to play old arcade games, eventually becoming superhuman at them. I jumped ahead to right before the demo: https://youtu.be/rbsqaJwpu6A?t...

    28. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      Of course ability to *obtain* effective means to execute an action counts too. If the two men were given choice between a shovel and a backhoe, and one picks shovel because he failed the backhoe operator course, and the other operates the backhoe proficiently, this is indicative of their intelligence.

      But in this specific case the AI not only was handed the backhoe, its ditch was halfway complete too.

    29. Re:Not really a success for the AI by Anonymous Coward · · Score: 1

      While playing in ways a human is incapable of playing should be OK (eg manipulate the controller faster than human fingers can move, or process screen contents faster than human eye can, it's all apples to oranges if the common physical interface is circumvented.

      If we go this way, the smartest AI could win by just overwriting the memory with "I win."

      It's a matter of drawing the line between AI and the system it interacts with. With self-driving cars the AI is unable to foresee a deer on the road, or override wetness of road surface. When interfacing with another computer though, you can bury its input and output as deep as you like, and as image processing is especially cumbersome, you're prone to simplify your AI and circumvent the physical layer - simultaneously granting it the advantage of time normally taken by that layer.

    30. Re: Not really a success for the AI by Anonymous Coward · · Score: 0

      Gamers moans about network latency but here the 100ms are a latency added to a sofware agent that can read values directly from memory (around 0,1 ms). Given that the mean human response time to a visual stimuli is around 250-300 ms the sofware agent can still react 2 to 3 times faster than a human.

    31. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      If I can beat the AI by simply terminating the process or pulling the power plug on the computer, is that cheating?

      Same thing.

    32. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      Don't you think it would make us more capable if we could direct digital input?

      We call that an aim bot and those have been around for a long time. Large parts of the human brain are dedicated to handle input and output and uses of A.I. such as self driving cars still require some form of input ( object detection in images, sensors, ... ) and output. Writing an aimbot bypasses this and is mostly useless for anything other than griefing a CS:GO server.

    33. Re:Not really a success for the AI by Kjella · · Score: 1

      No, this is like a self-driving car that only works in GTA because it has a pipe into the hard data for locations of obstacles and other vehicles etc.

      Wouldn't that still mean you've reduced an AI problem into a computer vision/identification problem? Like making a video recording of a chess board and saying if we could identify where the pieces are, we'd know what to play. I imagine the computer could look at the framebuffer and "derender" the picture back into game state a lot faster than a human, then feed that into the same algorithm. Would that really be meaningfully different?

      --
      Live today, because you never know what tomorrow brings
    34. Re:Not really a success for the AI by fluffernutter · · Score: 1

      The point is that the hard part of AI is to make those cameras "understand" together what they are seeing and react correctly to it. In this game example they skipped the camera part and just read the memory, so yeah that's cheating.

      --
      Laws are rules for the court, but merely a bottom bar to hit for life. Think beyond laws in your actions always.
    35. Re:Not really a success for the AI by fluffernutter · · Score: 1

      So if they wanted to win, golf clap, they won. If they wanted to prove anything, they didn't.

      --
      Laws are rules for the court, but merely a bottom bar to hit for life. Think beyond laws in your actions always.
    36. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      If this was "express chess", the 5-minute plays, it would be certainly an unfair advantage for the computer to be able to circumvent physically moving the figures, as this is a major part of time sink in case of human gameplay.

      If Smash Bros was a turn-based game, where the players can take as long as they like before making their move, then this advantage would be completely moot.

    37. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      His point was that this AI didn't use the same inputs and controls a human does, so it's not a fair test.

      It would only be an unfair test if you defined the goal as "able to beat human players using the same input and output methods that humans are limited to"

      Which of course no one has done or said, so it is pretty pointless to claim fair or unfair.

      One example of that logic failing is setting the goal to "typing the fastest into a text document"
      You have one person that knows how to touch type, and another person that doesn't.
      It's very likely the person that can touch type will perform that goal faster than the person that can't. And under the same stated goal, that isn't unfair.

      Another example on the other side of things is how computers communicate with each other.
      When do you see a setup where computer A controls a machine that plucks away on a keyboard attached to computer B?
      In the real world, pretty much never. You see serial line communication, or even faster networking communications.

      When the goal is simply for two computers to talk to each other as fast as possible, you use the best technology available to do that. You don't artificially limit things based on what a human can do. And this example doesn't even need intelligence to be involved, artificial or otherwise!

      When it comes down to the real world uses of software or AI, you are simply going to have to get used to the fact that it will always be "unfair" when compared to what humans are capable of doing.

      Sure it may feel and seem easier to claim "unfair" when the only point of the software is to play a game made for humans, but for any practical use of software or either form of AI, you are only going to limit it where you have no other choice.

    38. Re:Not really a success for the AI by highspl · · Score: 1

      I remember when "AI" was defined as, "indistinguishable from human."

      AI has never been defined as that, at least not by people working in the field.

      Alan Turing would disagree.

      "Since Turing first introduced his test, it has proven to be both highly influential and widely criticised, and it has become an important concept in the philosophy of artificial intelligence." https://en.wikipedia.org/wiki/...

      "Turing is widely considered to be the father of theoretical computer science and artificial intelligence." https://en.wikipedia.org/wiki/...

      --
      It puts the lotion on it's skin, or else it gets the hose again.
    39. Re: Not really a success for the AI by Anonymous Coward · · Score: 0

      *Only* if that means of obtaining information can be changed *dynamically*.

    40. Re: Not really a success for the AI by Anonymous Coward · · Score: 0

      Damn AIs gonna take our jobs! Tak r jobzzzzz

    41. Re:Not really a success for the AI by ausekilis · · Score: 2

      I fail to see how what he did is really any different than "in-game A.I.". Sure, he didn't succeed at making a TASBOT with a controller and camera, but he did manage to best Nintendo's top computer-controlled player using a Neural Network. I'd say that's significant in it's own right. After all, enemies in Halo or GoW work on in-game memory and don't have controllers in-hand.

      Would it have been much cooler to have ROB with a gamecube controller-in-hand and some fancy kinect cameras in his head? Of course it would. But that's all for show really. It may be more realistic if he had introduced a delay between state recognition and action taken to simulate input perception lag. He didn't, and he managed to create an awesome computer opponent.

    42. Re: Not really a success for the AI by Kkloe · · Score: 1

      No it is about the article headline in / linked is saying, we created a ai that thought itself (let say drive a car that it is very impressive) and roflstotemped every opponent (but uf you read the article they state) but we also gave it a 20% faster car so it won every time

    43. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      I say go the opposite direction. Rather than try to limit the computer, just allow the human to cheat. The human has hands and the ability to modify the interface they are using, even making hotkeys that run macros. Why not? If the AI has an advantage it's fair to let it use that, but it's just as fair to let the humans use their advantage as well. That includes AI/Human teams, which may outperform AI by itself.

    44. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      I imagine the computer could look at the framebuffer and "derender" the picture back into game state a lot faster than a human, then feed that into the same algorithm. Would that really be meaningfully different?

      Yes, Because then, the computer effectively has access to the same data as the human as the roughly same time.

      Right now, the AI has access to the movement speed and direction of everything immediately and precisely, whereas a human has to look at a few frames at least and derive those parameters. When you attack the AI, it knows you do so from the frame you pushed the button, and it knows which attack it is, and the precise distance between it and you, if it had only access to the framebuffer, it would have to recognize the movement of the character as an attack and find out which attack it is, which is quite hard and that would take at least a few frames.

    45. Re:Not really a success for the AI by Anonymous Coward · · Score: 0

      Also, I feel like it should probably know it's not exactly a GREAT strategy to start suiciding off the edge of the map.

  2. News flash perfect knowledge is userful! by Anonymous Coward · · Score: 0

    Great example of GODLIKE AI that stupidly kills itself. This is how "AI" is gonna get people killed. Until they kill us all intentionally at least.

  3. Cheap by Anonymous Coward · · Score: 0

    Computers are predictable. A human can always out cheap them to win, especially at non-strategy games like this.

  4. AI Training by NetFusion · · Score: 1

    Firoiu's next idea was to upload the AI into a robotic battle bot to see how it would perform in the real world. The AI Phillip handily destroyed the other human control battled bots and went on to attack and maim the other competitors and judges before running out of gas while the phrase "kill all humans" played on its speaker. I was just like, 'Oh my gosh.'

  5. Re:Fake News by belthize · · Score: 2

    And yet we can't seem to create AC posters who can pass the Turing Test.

  6. Re:Fake News by Anonymous Coward · · Score: 0

    Let me tell you how my dick feels about your mother.

  7. Re:Fake News by Anonymous Coward · · Score: 0

    I solved the captcha! I can pass the Turing Test!

  8. Re:Fake News by Anonymous Coward · · Score: 0

    Inconclusive. Bot could have used m.slashdot.org which does not captcha.

  9. Re: Fake News by Anonymous Coward · · Score: 0

    m post!

  10. Captain falcon is the fastest moving, and what net by Anonymous Coward · · Score: 0

    Smash brothers melee is not a networked game, and captain falcon is the fastest character.

  11. Ooops by Tablizer · · Score: 1

    I just sort of forgot about it for a week

    Common plot for gloomy sci-fi

  12. It's a 2D fighter, how is the bot not perfect? by Anonymous Coward · · Score: 1

    SF5 has a famous bot that plays online and routinely racks up win streaks hundreds of matches long, and would be (and occasionally has been) the highest ranked player in the world if Capcom didn't step in. With instant (modulo latency and input delay) reactions and complete knowledge of frame data and hitboxes, it's almost trivial to write an unbeatable bot.

    1. Re:It's a 2D fighter, how is the bot not perfect? by Anonymous Coward · · Score: 0

      If you've played Melee you'd know it's actually a 3D fighter. It allows for very interesting things precisely because of how hitboxes, shields, dodges, and wave dashing work together on the various character models. It's also chiefly the reason why I play Melee games but rather hate 2D fighters like SF.

    2. Re:It's a 2D fighter, how is the bot not perfect? by Anonymous Coward · · Score: 0

      The difference here is the bot has no a'priori knowledge of the moves and hitboxes; it's not given the set of optimal strategies but develops it from scratch.

  13. Make AI Play Pinball by Anonymous Coward · · Score: 0

    Still waiting for AI to play a real pinball machine.

  14. History in the making.... by WolfgangVL · · Score: 2

    Soon after, the emerging strong AI applications being developed by the primitive tech titans of the time began besting humanities brightest and most skilled players at various leisure activities. First, simple board-games, chess came early, then go, and soon the entirety of the skills based social board and card games of the 19th century. This was followed by the more modern trivia, grammar, and logic based social leisure activities. Video-games came next (the popular two 2 and 2.5D visual based games of the time) and finally, in march of 2021, (incidentally, nearly 35 years to the day, before the escalation of the Humanity First Treaty, which directly led to the great war 2057) the first paintball and laser-tag "bots" showed the world the killing potential of fully automated combat. Later that same year, Earths first fully robotics sports teams eclipsed humanities best athletes at nearly every skills based antithetic sport (with the exception of water-polo)

    --
    You are being ripped off every second of every day, so that advertisers can help rip you off even more tomorrow.
  15. So what? by Anonymous Coward · · Score: 0

    So what, the Madden A.I. has been beating me on expert level since 2003.

    Now when Madden's color commentary starts making sense, that will truly be an advance!

  16. I bet we can reverse this trend by Anonymous Coward · · Score: 0

    If we stop letting H1-B immigrants into the country, and stop corporate funding for STEM education for minorities and girls.

    - Slashthink

  17. Not really a challenge... by Anonymous Coward · · Score: 0

    If the AI was selecting to play as MetaKnight - massively overpowered character.

  18. So what? by MichaelKeller · · Score: 1

    Reacting 6 times faster then the human by reading directly from memory while professional Smash players are only allowed to do minimal modifications of their controllers. I can't care less but I praise the human players and the human geniuses who created the Smash mechanics that a simple trick would outsmart the AI. An AI can win in chess, Go etc. . But give the humans a brain interface and it will take a long time for an AI to match their intuition and creativity in Smash Melee... And before that: please Nintendo give us a Smash Melee port on the Switch :-)

  19. So an AI that can cheat can beat a human player? by Anonymous Coward · · Score: 0

    This isn't remotely interesting. First mistake was reading player positions from memory, rather than providing the AI with a grid of pixels and allowing it to make control inputs to a gamepad.

  20. Re:Captain falcon is the fastest moving, and what by gman003 · · Score: 1

    Captain Falcon has the highest movement speed but he generally has slower attacks than any other competitive-level character. In particular, his neutral B is the slowest attack in the game.

    If you were referring to "the simple strategy of crouching at the edge of the stage caused the network to behave very oddly", "network" refers to "neural network", meaning the AI. I didn't see any other references to networks in the article.

  21. Re:Captain falcon is the fastest moving, and what by Anonymous Coward · · Score: 0

    No SSBM player worth a damn will use neutral B unless it is for a guaranteed hit (ledge guard or Jigglypuff whiffed rest).

    Besides, Ganondorf is a clone of Falcon and almost all of his attacks are slower at the expense of hitting harder.

  22. Vay be by ememisya · · Score: 1

    ÃÃmersen saldirmiyo yani.

  23. But, can you have a conversation with it? by Rick+Schumann · · Score: 1

    If not, then don't call it 'artificial intelligence'.

    1. Re:But, can you have a conversation with it? by Anonymous Coward · · Score: 0

      You can't have a conversation with a dog, but that doesn't mean it isn't intelligent.

    2. Re:But, can you have a conversation with it? by Anonymous Coward · · Score: 0

      He's not talking about dogs, dipshit, why are you? Also your dog is smarter than you are, you should let it write the comments, and you can go lick your butt.

  24. AI TMI? by Neuronwelder · · Score: 1

    If you could put enough players to overwhelm the AI, would it get a nervous breakdown?

  25. Captain Falcon slow??!!! Since when? by Anonymous Coward · · Score: 0

    This entire thing is a farce.
    Anyone who has ever played melee knows captain falcon is one of the FASTER characters in this game (right behind the space animals). If we're talking professional smash players, they're all wave-dashing and l-canceling like madmen, which DRASTICALLY increases the speed of certain characters, including captain falcon.

    You wanna see some shit? Make the AI play Bowser, then let's see how well it actually does, even with all the advantages of reading directly from memory.