Creating an environment to quickly train a variety of Deep Reinforcement Learning algorithms on Street Fighter 2 using tournaments between learning agents
Create an agent that learns to play a game (e.g., Atari, chess) using reinforcement learning algorithms like Deep Q-Networks (DQN) or Proximal Policy Optimization (PPO).
mpmg is a modular environment designed for studying the Minimum Price Markov Game (MPMG), a concept in game theory and algorithmic game theory. It provides an easy-to-use framework for conducting experiments with multiple AI-agents using collusion and cooperation dynamics.
Tech-Stack: Java. An EA evolved the weights of a neural network to land spaceships.
Add a description, image, and links to the game-environment topic page so that developers can more easily learn about it.
To associate your repository with the game-environment topic, visit your repo's landing page and select "manage topics."