Getting Started with Casino of Life

Welcome to Casino of Life! This guide will help you get up and running with our revolutionary framework for training AI agents in retro fighting games using natural language interactions.

What is Casino of Life?

Casino of Life combines reinforcement learning with natural language processing to create an intuitive interface for training game-playing AI agents. Our platform allows you to:

Train AI agents using natural conversations
Explain strategies in plain English
Get real-time feedback on training progress
Interact with CaballoLoko, your AI training assistant

Installation

Getting started with Casino of Life is simple. Install the package using pip:

pip install casino-of-life

Basic Usage

Here's a quick example to get you started:

from casino_of_life.agents import DynamicAgent, CaballoLoko
from casino_of_life.environment import RetroEnv

# Initialize CaballoLoko for training guidance
caballo_loko = CaballoLoko()
response = caballo_loko.chat("Train Liu Kang to be aggressive with fireballs")

# Create environment and agent
env = RetroEnv(
    game='MortalKombatII-Genesis',
    state='tournament',
    players=2
)

agent = DynamicAgent(
    env=env,
    policy='PPO',
    learning_rate=0.0003
)

# Start training with natural language guidance
agent.train(
    timesteps=100000
)

Supported Games

Currently, we support the following games:

Mortal Kombat II (Genesis)
Street Fighter II (Coming Soon)
More fighting games to be added

Prerequisites

Before using Casino of Life, make sure you have:

Python 3.8+ installed
Basic understanding of reinforcement learning concepts
ROM files for the games you want to use (not included with the package for legal reasons)

Next Steps

Now that you have the basics, explore the following guides to take full advantage of Casino of Life:

PreviousCimai's Casino of Life Docs NextNatural Language Training Interface

Last updated 3 months ago

from casino_of_life.agents import DynamicAgent, CaballoLoko from casino_of_life.environment import RetroEnv # Initialize CaballoLoko for training guidance caballo_loko = CaballoLoko() response = caballo_loko.chat("Train Liu Kang to be aggressive with fireballs") # Create environment and agent env = RetroEnv( game='MortalKombatII-Genesis', state='tournament', players=2 ) agent = DynamicAgent( env=env, policy='PPO', learning_rate=0.0003 ) # Start training with natural language guidance agent.train( timesteps=100000 )