← Goal templates

Reinforcement learning, from basics to PPO

Agents, rewards and policies, up to the algorithm behind RLHF.

Learn reinforcement learning properly: Markov decision processes, value functions, Q-learning and policy gradients, with David Silver's first lecture, OpenAI's Spinning Up and Lilian Weng's guide, then read the DQN and PPO papers.

intermediateabout 4 weeks at 60 min a day5 free sources

What you'll cover

  1. Phase 1

    Foundations

    • Agents, environments and rewards
    • Markov decision processes
    • Value functions and Bellman equations

  2. Phase 2

    Value-based methods

    • Q-learning
    • Deep Q-networks
    • Experience replay and target networks

  3. Phase 3

    Policy methods

    • Policy gradients and REINFORCE
    • Actor-critic methods
    • Trust regions and PPO

An outline. Your own plan is made when you start, around your level and deadline.

Sources

Free, and fetched for you

All sources belong to their creators and are free to watch or read; Confu links to them and turns them into study PDFs for you.

More templates