Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Five at Dota 2 – The International [video]

youtube.com

Post reply on HN
Print view View original

161–170 of 172 posts

Re: OpenAI Five at Dota 2 – The International [video]

#161

Post by _ptgt »

ajuc wrote: post #112
_ptgt wrote: post #51

Earlier quoted context omitted.

> Once OpenAI Five defeat 3-4 pro teams convincingly, it could be presumed from the observation above that they will defeat any other top teams within a year at most, if sufficient resources are used for improving the AI. An exception is when a fundamental hidden weakness is found in the AI. Not sure how you intended this, but the hero pool constraint is actually an enormous advantage for the AI. The current hero poo…

> I don't know OpenAI selected it, but it's highly conducive to OpenAI Five's strengths--deathballing, mechanics, teamfight coordination, etc. It lacks essentially all of the heroes that humans would normally pick to counter that strategy. Isn't it the other way around - openai adjusted to the hero pool to come up with its' strategy, because it was trained on this hero pool. If hero pool had only late-game melee carr…

I don't think so. It's quite easy to imagine that a computer would outperform humans in strategies that require precise execution and coordination in teamfights. In fact, it's not specific to OpenAI; even the built-in Dota bots' strengths are generally teamfight execution.

My guess is that if OpenAI 5 trained under a different hero pool, it would be weaker than it is now. It's very hard to predict how much weaker though.

Re: OpenAI Five at Dota 2 – The International [video]

#162

Post by balls187 »

ionforce wrote: post #90
balls187 wrote: post #34

Earlier quoted context omitted.

I recall reading somewhere that the real advantage AI had was in it's ability to come up with bizarre strategies that confuse human opponents.

I'm skeptical that you read this somewhere. AI doesn't "come up" with strategies. It's likely something that's been discovered in training and then mechanically repeated. But it doesn't "come up" with strategies out of nowhere.

"Come up" is my short form for the process in which AIs are built.

The actual point is that AI's advantage were using tactics and strategies that human opponents would find unintuitive, or even counter-intuitive.

How AI comes up with those tactics is not at all relevant to this thread.

Re: OpenAI Five at Dota 2 – The International [video]

#163

Post by balls187 »

tree_of_item wrote: post #133
ionforce wrote: post #90

Earlier quoted context omitted.

I'm skeptical that you read this somewhere. AI doesn't "come up" with strategies. It's likely something that's been discovered in training and then mechanically repeated. But it doesn't "come up" with strategies out of nowhere.

Why doesn't it come up with strategies? The program is doing a massive search over an action space, of course it will find things there.

It's a dumb semantics argument about using the phrase "come up."

Re: OpenAI Five at Dota 2 – The International [video]

#164

Post by balls187 »

foota wrote: post #44
balls187 wrote: post #27

Earlier quoted context omitted.

Dropped the first game. Pretty funny that the last openAI bot attempted to feed mid.

Not familiar with dota but I watched the tail end of the stream, what does this mean?

dx87 gave a good explanation.

"Feed" is a term in Dota when players (aka Heroes) die without any benefit to your team--such as destroying an enemy spawn (racks/Barracks), killing another team Hero (hopefully more one). It's "feeding" as the other team members nearby will get gold and experience for each kill. As there is a respawn timer, the character who is dead will not get Exp nor Gold during that count-down resulting in a character that is disadvantaged as it will be under leveled compared to the rest of the heroes.

In the early and mid games of Dota, not gaining experience and gold is a major setback. Dying has a huge penalty.

The term "feed" is used with players who are learning the game, or those who are low skilled, and are haven't yet mastered some of the main aspects of playing. They're dying with no benefit, boosting the other team.

"Mid" simply means 'middle lane.' DOTA has 3 lanes, top, middle, and bottom, and short hand refers to them as top, mid, bot, respectively.

If your team is losing, boosting the other team to get the game over with is poor sportsmanship. A single team battle could easily shift the game into the losing teams favor.

In sports like Football, you may see teams pull their starters to 1. prevent injury and 2. give other teammates experience, but you'd never see someone purposefully help the opposing team win.

Re: OpenAI Five at Dota 2 – The International [video]

#165

Post by Ntrails »

WhompingWindows wrote: post #150
emilsedgh wrote: post #129

Earlier quoted context omitted.

If a team of humans made such horrible mistakes, they would never be able to compete nowhere near this level. Is OpenAI's team-fight "so good" that compensates for these huge mistakes and allows them to compete with pro teams? For me as a player, the team fights are quite confusing and overwhelming. The most complex part of the game. If the OpenAI team got the teamfights covered that well, I'm pretty much sure they c…

Warding is a tough one. Outside of hard-coding it, how would you suggest the AI would learn the best locations for warding and de-warding? Can they surmise that an opponent's gank or quick reaction to their movement means there may be an obs ward? If so, where precisely is that? I don't know if the OpenAI supports can play the warding mind-games, which also for me personally involve 1000+ games' experience. I see int…

> Can the OpenAI team learn to do this sort of behavior?

This is the core of what I want from open ai and feel like I'm not seeing. I want the AI to _reason_ that blocking the creepwave brings the equilibrium back to your tower and results in an easier lane. Not just to say "this thing works so I'll do it a lot" - but to say "if I do this then it will have this impact on the game state".

What we got was the devs specifically training models for goals like creep blocking. Which, you know, just seems a bit meh

Re: OpenAI Five at Dota 2 – The International [video]

#166

Post by zamalek »

rishav_sharan wrote: post #120

There are a lot of areas that OpenAI needs to improve on. the bots generally; 1. terrible at warding and dewarding 2. are terrible at using spell spam to farm. while their aoe spell usage is great in team fights, they suck at using spells to farm when they are alone. Gyro used his ult to farm a normal sized lane and still missed half the creeps. 3. don't understand bouncing spells like the lich nuke. In fact many tim…

Some of these run on the assumption that "we know best."

1. May be an unimportant waste of time and money given some unknown superior strategy.

2/3/10. May be similar to Alpha Go/Alpha Zero. A win by 1% is still a win.

11. Is a known issue.

Re: OpenAI Five at Dota 2 – The International [video]

#168

Post by akyu »

JoeAltmaier wrote: post #145
akyu wrote: post #144

Earlier quoted context omitted.

Those were some exceptional children.

Yeah it can't have been so low can it? But it was double digits. Anyway, the fastest ones would put their eye right up to the scope, so the pulse would have the largest signal right into their eye. I thought that was clever.

My guess is there was some tell that they were using to predict the timing.

Re: OpenAI Five at Dota 2 – The International [video]

#169

Post by drusepth »

nindalf wrote: post #67
noxvilleza wrote: post #53

Earlier quoted context omitted.

It's actually internationally delayed reactions to make it more fair (200ms of delay added).

200 ms is much better than 99.99% of humans though. One specific example - one of the humans playing Axe tried to cast a spell that would taunt an enemy into attacking him. It takes 400ms to cast this. That’s not enough time for all but a handful of humans to react, but OpenAI managed it with ease. He couldn’t land the spell until he purchased an item that granted him invisibility.

>200 ms is much better than 99.99% of humans though

I think this is bit of a red herring: while that's true, OpenAI isn't competing against 99.99% of humans -- they're competing against the top 0.05% of Dota players that very likely have a much, much lower average reaction rate.

To throw numbers at it, https://www.humanbenchmark.com/tests/reactiontime/ has the top 10 people at ~110ms[1], while I (at a measly 1K MMR in Dota) can pretty easily average ~220ms (and they report human average around. I imagine pros in the scene have honed these reflexes to be far superior than the average human.

[1] Also worth noting that they discard all reactions <100ms, so we could have some <100ms prodigies that actually have faster reaction time than the 100ms reported on the scoreboard for them. (These numbers are spread over 5+ trials, so "getting lucky" is a lot less likely.)

Re: OpenAI Five at Dota 2 – The International [video]

#170

Post by forgot-my-pw »

rishav_sharan wrote: post #120

There are a lot of areas that OpenAI needs to improve on. the bots generally; 1. terrible at warding and dewarding 2. are terrible at using spell spam to farm. while their aoe spell usage is great in team fights, they suck at using spells to farm when they are alone. Gyro used his ult to farm a normal sized lane and still missed half the creeps. 3. don't understand bouncing spells like the lich nuke. In fact many tim…

Isn't it impressive that they're able to compete at such high level with these knowledge gaps.
Post reply on HN