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

Ask HN: Building a game for AI Research

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 38 posts

Re: Ask HN: Building a game for AI Research

#11

Post by yathern »

godelmachine wrote: post #10
nrmn wrote: post #3

From my viewpoint, as both a researcher and someone who has built frameworks around environments/games: - Each step within the game has to be extremely fast. I.e the game should be able to be run as fast as the machine allows while keeping physics etc. consistent. - Runnable via library import such that there is no drawing to the screen. - Should be easy to reset the environment to an initial state. - RNG state shoul…

May I ask what do you mean by "RNG state should be seedable"?

If the game depends on random events (eg an attack does random damage between 3-8) it would be useful to make sure it's always the same randomness, if you want it at least.

Re: Ask HN: Building a game for AI Research

#12

Post by luchris429 »

If you're using Unity, I would recommend that you check out Unity Machine-Learning Agents!

https://github.com/Unity-Technologies/ml-agents

It makes it really easy to make games for reinforcement learning. I worked on it a bit over summer, so if you have any questions, feel free to reach out to me.

Re: Ask HN: Building a game for AI Research

#13

Post by psandersen »

There are plenty of great answers here already, but what I think would help improve the state of the art would be configurable reward sparsity and configurable priors.

- Reward sparsity means that an easier version of the game gives a score after very few moves, but a more difficult version might take many many moves. It would be useful to see how agents compare against humans as the rewards get sparser.

- Configurable priors are vaguer and are to make it easier to have the game match expectations from prior experience in other games. E.g. researchers could overlay a custom texture on enemies that look like enemies from other games to test and develop better transfer learning algorithms.

Re: Ask HN: Building a game for AI Research

#14

Post by scrollaway »

nrmn wrote: post #3

From my viewpoint, as both a researcher and someone who has built frameworks around environments/games: - Each step within the game has to be extremely fast. I.e the game should be able to be run as fast as the machine allows while keeping physics etc. consistent. - Runnable via library import such that there is no drawing to the screen. - Should be easy to reset the environment to an initial state. - RNG state shoul…

Excellent list.

> - Should be easy to reset the environment to an initial state.

Adding on to that, the ability to rewind the game state is a pretty big deal.

The biggest deal for AI researchers though is that you implement a replay function and format, and publish lots of tooling around them (to read and parse them, etc; at least in Python).

Also, if it's an online game, save the replays serverside and publish them somewhere. Kaggle will be happy to take it I'm sure.

Re: Ask HN: Building a game for AI Research

#16

Post by rhlala »

I would love to see a game that needs cooperation between x agents to wins.

I feel like play as a team in a imperfect information environnement is one of the most interesting AI challenge out there.

Imagine a 2d csgo with no need of manual skill, no aim or reflex, just player placement, crosshair(view) placement and teamplay.

If you know some game like this let me know please, if there is not i will build it one day.

Re: Ask HN: Building a game for AI Research

#17

Post by Tepix »

ddtaylor wrote: post #9

I have been working on a simple project for evolving 5v5 ship battles similar to asteroids. My advice is make it easy to serialize the game state. 99% of the simulations will do the same thing or waste 1000s of frame getting to the "important part" of the match, and the ability to save the game state and re-play it from a specific position can be beneficial. However, from what I understand, this limits your game to a…

Sounds like Netrek (which is 8vs8) and in space (but 2d).

Re: Ask HN: Building a game for AI Research

#18

Post by Tepix »

rhlala wrote: post #16

I would love to see a game that needs cooperation between x agents to wins. I feel like play as a team in a imperfect information environnement is one of the most interesting AI challenge out there. Imagine a 2d csgo with no need of manual skill, no aim or reflex, just player placement, crosshair(view) placement and teamplay. If you know some game like this let me know please, if there is not i will build it one day.

Do you know the game netrek? It's a 8vs8 game that heavily relies on teamplay. It was one of the first real-time games to be played over the internet. It also has this imperfect information aspect (fog of war, inaccurate display of cloaked ships, need to scout planets). Free and open source. http://netrek.org

Re: Ask HN: Building a game for AI Research

#19

Post by RobertoG »

>"I tried reading TF/PyTorch docs but couldn't find a guide on how to make my game a friendly environment"

Are you aware of 'Elf' and 'TorchCraft' by Facebook (creators of Pytorch)?

From https://facebook.ai/developers/tools/elf :

"ELF provides an end-to-end solution for game research. It includes miniature real-time strategy game environments, concurrent simulation, distributed training over thousands of machines, intuitive APIs, web-based visualizations, and a reinforcement learning framework powered by PyTorch."

From https://facebook.ai/developers/tools/torchcraft :

"TorchCraft is a Brood War API (BWAPI) module that sends StarCraft data out over a ZMQ connection, allowing researchers to parse StarCraft data and interact with BWAPI from C++, Python (PyTorch-friendly), and Lua (Torch-friendly)."

Re: Ask HN: Building a game for AI Research

#20

Post by gmueckl »

rhlala wrote: post #16

I would love to see a game that needs cooperation between x agents to wins. I feel like play as a team in a imperfect information environnement is one of the most interesting AI challenge out there. Imagine a 2d csgo with no need of manual skill, no aim or reflex, just player placement, crosshair(view) placement and teamplay. If you know some game like this let me know please, if there is not i will build it one day.

Sounds like Robocup Simulations League comes very close.
Post reply on HN