Skip to content

Reinforcement Learning series

Let's explore the world of reinforcement learning with Alessandro Palmas, the creator of DIAMBRA, a virtual dueling arena where you can train your agents on popular games, all in Python.

Some of the features that DIAMBRA offers include:

  • Competitive Multi-Agent
  • Competitive Human-Agent
  • Self-Play
  • Imitation Learning
  • Human-in-the-loop Training

Structure of the series

  1. Theoretical concepts and environment setup
  2. Practical session and coding

Material

Github