Artificial Intelligence & Data Science is coming soon

We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.

Artificial Intelligence & Data Science

Reinforcement Learning

Bandits and MDPs, Bellman equations, Monte Carlo and TD, DQN and policy gradients, RLHF.

Interview questions

Coming next in Reinforcement Learning

  1. Agent-environment interface· notes coming
  2. Rewards, returns and discounting· notes coming
  3. Types of reinforcement learning· notes coming
  4. Multi-armed bandits· notes coming
  5. Exploration strategies· notes coming
  6. Markov chains and reward processes· notes coming
  7. Value functions· notes coming
  8. Bellman equations· notes coming
  9. Optimal policies· notes coming
  10. Monte Carlo prediction· notes coming
  11. Monte Carlo control· notes coming
  12. Importance sampling· notes coming
  13. Temporal difference learning· notes coming
  14. SARSA· notes coming
  15. Deep Q-networks· notes coming
  16. Double and dueling DQN· notes coming
  17. Policy gradients: REINFORCE· notes coming
  18. Actor-critic methods· notes coming
  19. Proximal policy optimisation· notes coming
  20. Reinforcement learning from human feedback· notes coming
  21. Reward modelling· notes coming
  22. Multi-agent reinforcement learning· notes coming
  23. Offline reinforcement learning· notes coming
  24. History and scope of reinforcement learning· notes coming
  25. Policy iteration· notes coming
  26. Partially observable MDPs· notes coming
  27. Dynamic programming for MDPs· notes coming
  28. Value iteration· notes coming
  29. Contraction mapping and convergence· notes coming
  30. Monte Carlo tree search· notes coming
  31. Dyna: integrated planning and learning· notes coming
  32. Prioritised sweeping· notes coming
  33. Rollout algorithms· notes coming
  34. Value-function approximation· notes coming
  35. Semi-gradient methods and linear function approximation· notes coming
  36. Policy gradient theorem· notes coming
  37. Markov games, Nash and correlated equilibria· notes coming
  38. Applications of reinforcement learning· notes coming
  39. PAC bandit algorithms and median elimination· notes coming
  40. Least-squares methods and fitted Q-iteration· notes coming
  41. Hierarchical reinforcement learning· notes coming