Your country

Tools that support it use your country for local currency, number formats, units and paper size. Your choice is saved only in this browser.

Type a name or a two-letter code. Use the up and down arrow keys to move through the countries, Enter to choose one and Escape to close.

AI and machine learning

Reinforcement Learning (Gymnasium and PyTorch)

The planned outline of 16 modules. Lessons are written, run and reviewed before they are published.

Coming soon 16 modules

Coming soon. This track is being written. Below is its planned outline: a lesson appears here once its examples have been run and its technical review is signed off.

Planned outline

  1. Module 1

    Start here: the RL problem and your toolkit

    Coming soon
  2. Module 2

    From bandits to Markov decision processes

    Coming soon
  3. Module 3

    Planning with a known model: dynamic programming

    Coming soon
  4. Module 4

    Learning from complete episodes: Monte Carlo

    Coming soon
  5. Module 5

    Temporal-difference learning

    Coming soon
  6. Module 6

    Function approximation

    Coming soon
  7. Module 7

    Deep Q-networks

    Coming soon
  8. Module 8

    Policy gradient methods

    Coming soon
  9. Module 9

    Trust regions and PPO

    Coming soon
  10. Module 10

    Off-policy actor-critic for continuous control

    Coming soon
  11. Module 11

    Practical RL: environments, tools and evaluation

    Coming soon
  12. Module 12

    Exploration, imitation and world models

    Coming soon
  13. Module 13

    Offline RL and off-policy evaluation

    Coming soon
  14. Module 14

    Games, search and multi-agent RL

    Coming soon
  15. Module 15

    RL for language models: RLHF, RLVR and GRPO

    Coming soon
  16. Module 16

    RL in the real world

    Coming soon

Related tools

Official documentation

More in AI and machine learning

Quick answers and tool search

Type to search tools or to get a quick answer, for example 18% of 2500. Use the up and down arrow keys to move through the results, Enter to choose, and Escape to close.