Welcome to MARL-API’s documentation!

Github repository: https://github.com/blavad/marl

Quick start:

• Installation
  • Prerequisites
  • Ubuntu
  • Mac OS
• Examples
  • Check available classes
  • Single-agent example
  • Multi-agent example
  • Training two independant DQN agents
• Environment requirements
  • OpenAI Gym based environment
  • Markov Games formalism

Contents:

• Multi-agent RL
• Agents
  • Base Agent
  • Q-value based model
  • Policy Gradient based model
  • Multi-agent Policy Gradient based model
• Experience
  • Experience
  • ReplayBuffer
• Exploration
  • Exploration
  • Eps-Greedy
  • Ornstein–Uhlenbeck Process
• Policies
  • Base Policy
  • Several Policies
• Models
  • Value and Q-Value array
  • Neural network model

Indices and tables

• Index

• Module Index

• Search Page