showdown
ai-tools
showdown | ai-tools | |
---|---|---|
5 | 1 | |
237 | 1 | |
- | - | |
6.3 | 10.0 | |
13 days ago | 11 months ago | |
Python | Ruby | |
GNU General Public License v3.0 only | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
showdown
-
AI vs AI Pokemon Tournament - Hoenn Edition.
Like last time I will be using this pokemon showdown bot to make this work. The teams have ben fed into it, and two instances of the bot are running. Bot 1 will challenge Bot 2 to a Gen 7 anything goes match on Pokemon Showdown. The replay is then saved to my PC and live commentary is recorded.
-
Is there ANY way of doing customizable AI vs AI battles that DOESN'T require extensive programming knowledge??
I know about the Showdown bot by Pmariglia. In fact I spoke to the creator for more than two hours on discord trying to get it to work, this involved me downloading python, docker, gitbash, all sorts of command prompt tomfoolery.
-
AI vs AI Pokemon Tournament - The Great Indigo Plateau Tournament.
First a bit of background. While looking for ways to do this I came across this Pokemon Showdown bot, created by Pmariglia. So shout out to them, as this wouldn't have been possible with the work they had already done!
-
How an A.I. is Becoming the World's Best Pokemon Player
He doesn't reveal any big details about the algorithm, but from what I can tell his final iteration is some kind of expectiminimax + pruning, where essentially the bot is looking forward a few turns and based on all possible (or usually all "reasonable") outcomes, picks the moves that minimize the worst outcome, aka your traditional "safe" player. There are definitely limitations to this approach, first of all is the depth of search. To give context, Stockfish regularly searches to 30 moves ahead. I am pretty sure that a lot of implementations are limited to a mere 3 moves ahead, as illustrated here (https://github.com/pmariglia/showdown/issues/53). So, I suspect that ~1600 is going to be a pretty hard limit because you can't use this approach by itself to really develop long-term strategies. Another thing I wanted to point out is that this algorithm is also really prone to exploitability- knowing that your opponent is always a safe player is going to lead to easy manipulation by the best players. He even mentions it here in his Smogon post:
-
Is there anyway to have a Computer fight a Computer? Im trying to have a Bot with Cynthia's team fight Leons team, to settle the debate
A quick google has found an AI program that you could use. https://github.com/pmariglia/showdown Now I don't know if this will simply play for you, or allow you to play against it, but either way there'd be a way to do it.
ai-tools
-
I created a command-line README Generator
If you're interested, you can find the repository here: https://github.com/jaredcd/ai-tools. This repo's README was generated with the tool, so it's a good example.
What are some alternatives?
libmelee - Open Python 3 API for making your own Smash Bros: Melee AI that works with Slippi Online
Dependency Injector - Dependency injection framework for Python
AI-Image-PromptGenerator - A flexible UI script to help create and expand on prompts for generative AI art models, such as Stable Diffusion and MidJourney. Get inspired, and create.
Piccolo - Piccolo (formerly Pilot) – mini game engine for games104
program-y - Python 3.x based AIML 2.0 Chatbot interpreter, framework, related programs and knowledge files
fastapi - FastAPI framework, high performance, easy to learn, fast to code, ready for production
irwin - irwin - the protector of lichess from all chess players villainous
python-slack-sdk - Slack Developer Kit for Python
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
fastapi-distributed-websocket - A library to implement websocket for distibuted system based on FastAPI.
tango - Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.