6. MLPro-RL - Reinforcement Learning

• 6.1. Overview
• 6.2. Getting started
• 6.3. Environments
  • 6.3.1. Developing custom environments
  • 6.3.2. Reusing environments from the pool
    • 6.3.2.1. Bulk Good Laboratory Plant (BGLP)
    • 6.3.2.2. Multi-Cartpole
    • 6.3.2.3. Grid World
    • 6.3.2.4. Robot Manipulator on Homogeneous Matrix
    • 6.3.2.5. Double Pendulum
    • 6.3.2.6. 2D Collision Avoidance
• 6.4. Agents
  • 6.4.1. Custom policies
  • 6.4.2. Policy pool
    • 6.4.2.1. Random Action Generator
    • 6.4.2.2. Model Predictive Control (MPC)
  • 6.4.3. Model-based agents
  • 6.4.4. Multi-agents
• 6.5. Scenarios
• 6.6. Training and tuning
• 6.7. 3rd party support