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.
Your progress in this subject0 of 1 · 0%
Coming next in Reinforcement Learning
- Agent-environment interface· notes coming
- Rewards, returns and discounting· notes coming
- Types of reinforcement learning· notes coming
- Multi-armed bandits· notes coming
- Exploration strategies· notes coming
- Markov chains and reward processes· notes coming
- Value functions· notes coming
- Bellman equations· notes coming
- Optimal policies· notes coming
- Monte Carlo prediction· notes coming
- Monte Carlo control· notes coming
- Importance sampling· notes coming
- Temporal difference learning· notes coming
- SARSA· notes coming
- Deep Q-networks· notes coming
- Double and dueling DQN· notes coming
- Policy gradients: REINFORCE· notes coming
- Actor-critic methods· notes coming
- Proximal policy optimisation· notes coming
- Reinforcement learning from human feedback· notes coming
- Reward modelling· notes coming
- Multi-agent reinforcement learning· notes coming
- Offline reinforcement learning· notes coming
- History and scope of reinforcement learning· notes coming
- Policy iteration· notes coming
- Partially observable MDPs· notes coming
- Dynamic programming for MDPs· notes coming
- Value iteration· notes coming
- Contraction mapping and convergence· notes coming
- Monte Carlo tree search· notes coming
- Dyna: integrated planning and learning· notes coming
- Prioritised sweeping· notes coming
- Rollout algorithms· notes coming
- Value-function approximation· notes coming
- Semi-gradient methods and linear function approximation· notes coming
- Policy gradient theorem· notes coming
- Markov games, Nash and correlated equilibria· notes coming
- Applications of reinforcement learning· notes coming
- PAC bandit algorithms and median elimination· notes coming
- Least-squares methods and fitted Q-iteration· notes coming
- Hierarchical reinforcement learning· notes coming