MLPro Documentations Logo

Welcome to MLPro

  • 1. Introduction
  • 2. Getting Started

Basic Functions

  • 3. MLPro-BF - Basic Functions

Machine Learning

  • 4. MLPro-SL - Supervised Learning
  • 5. MLPro-OA - Online Adaptivity
  • 6. MLPro-RL - Reinforcement Learning
  • 7. MLPro-GT - Game Theory

Extension Hub

  • 8. General Information
  • 9. Third-Party Extensions

Appendices

  • A1 - Example Pool
    • MLPro-BF - Basic Functions
    • MLPro-SL - Supervised Learning
    • MLPro-RL - Reinforcement Learning
      • Elementary or Uncategorized Topics
      • Agents
        • Howto RL-AGENT-001: Run an Agent with Own Policy
        • Howto RL-AGENT-002: Train an Agent with Own Policy
        • Howto RL-AGENT-003: Run Multi-Agent with Own Policy
        • Howto RL-AGENT-004: Train Multi-Agent with Own Policy
        • Howto RL-AGENT-011: Train and Reload Single Agent (Gym)
        • Howto RL-AGENT-021: Train and Reload Single Agent Cartpole Discrete (MuJoCo)
        • Howto RL-AGENT-022: Train and Reload Single Agent Cartpole Continuous (MuJoCo)
      • Environments
      • Adaptive Environments
      • Model-based Reinforcement Learning
      • Advanced Training Techniques
      • Hyperparameter Tuning Tools
      • Wrappers
      • User Interaction
    • MLPro-GT - Game Theory
    • MLPro-OA - Online Adaptivity
  • A2 - API Reference
  • A3 - Project MLPro
MLPro Documentations
  • A1 - Example Pool
  • MLPro-RL - Reinforcement Learning
  • Agents
  • Edit on GitHub

Agents

  • Howto RL-AGENT-001: Run an Agent with Own Policy
  • Howto RL-AGENT-002: Train an Agent with Own Policy
  • Howto RL-AGENT-003: Run Multi-Agent with Own Policy
  • Howto RL-AGENT-004: Train Multi-Agent with Own Policy
  • Howto RL-AGENT-011: Train and Reload Single Agent (Gym)
  • Howto RL-AGENT-021: Train and Reload Single Agent Cartpole Discrete (MuJoCo)
  • Howto RL-AGENT-022: Train and Reload Single Agent Cartpole Continuous (MuJoCo)
Previous Next

© Copyright 2023 South Westphalia University of Applied Sciences, Germany.

Built with Sphinx using a theme provided by Read the Docs.