Information Technology 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.

Information Technology

Reinforcement Learning

Introduction to reinforcement learning, bandit problems and online learning, Markov decision processes, dynamic programming.

Interview questions

Coming next in Reinforcement Learning

  1. Elements of reinforcement learning· notes coming
  2. Types of reinforcement learning and rewards· notes coming
  3. Q-learning and SARSA· notes coming
  4. The n-armed bandit problem· notes coming
  5. Action-value methods· notes coming
  6. Optimistic initial values and UCB action selection· notes coming
  7. Gradient bandits· notes coming
  8. The agent–environment interface· notes coming
  9. Returns and the Markov property· notes coming
  10. Value functions and optimal value functions· notes coming
  11. Policy evaluation and improvement· notes coming
  12. Policy iteration· notes coming
  13. Value iteration· notes coming
  14. Asynchronous DP and generalised policy iteration· notes coming
  15. Monte Carlo prediction and control· notes coming
  16. Temporal-difference prediction· notes coming
  17. Off-policy prediction with importance sampling· notes coming
  18. RL case studies: elevator dispatching, channel allocation and job-shop scheduling· notes coming
  19. PAC bandit algorithms and median elimination· notes coming
  20. Eligibility traces and TD(λ)· notes coming
  21. Value-function approximation· notes coming
  22. Semi-gradient methods and linear function approximation· notes coming
  23. Deep Q-networks· notes coming
  24. Policy gradient theorem· notes coming
  25. Hierarchical reinforcement learning· notes coming
  26. Partially observable MDPs· notes coming