Computer Engineering 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.

Computer Engineering

Reinforcement Learning

Bandits and MDPs, dynamic programming, Monte Carlo and TD learning, policy gradients, deep RL.

Interview questions
Notes for Reinforcement Learning are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.

Coming next in Reinforcement Learning

  1. Reinforcement learning: elements and scope· notes coming
  2. Multi-armed bandits· notes coming
  3. Action selection: optimistic values, UCB and gradient bandits· notes coming
  4. Finite Markov decision processes· notes coming
  5. Policies, value functions and optimality· notes coming
  6. Policy evaluation and policy iteration· notes coming
  7. Value iteration and generalised policy iteration· notes coming
  8. Monte Carlo prediction and control· notes coming
  9. Off-policy learning and importance sampling· notes coming
  10. Temporal-difference prediction· notes coming
  11. Sarsa and Q-learning· notes coming
  12. Expected Sarsa and double learning· notes coming
  13. n-step bootstrapping· notes coming
  14. Planning with models, prioritised sweeping and MCTS· notes coming
  15. Value-function approximation· notes coming
  16. Semi-gradient methods and linear function approximation· notes coming
  17. On-policy control with approximation· notes coming
  18. Off-policy approximation and the deadly triad· notes coming
  19. Eligibility traces and TD(λ)· notes coming
  20. Policy gradient theorem· notes coming
  21. REINFORCE and baselines· notes coming
  22. Actor–critic methods· notes coming
  23. Deep Q-networks· notes coming
  24. DQN improvements: double DQN, prioritised replay and dueling· notes coming
  25. Continuous actions: DDPG and PPO· notes coming
  26. Trends: multi-agent RL, offline RL and RLHF· notes coming
  27. PAC bandit algorithms and median elimination· notes coming
  28. Hierarchical reinforcement learning· notes coming
  29. Partially observable MDPs· notes coming