Log in Sign up

Home
RGPV
AD
8th Semester
AD-802 (B)
Unit 2 Notes

AD-802 (B) Reinforcement Learning Unit 2 Notes

Notes and important questions for unit 2: Bandit Algorithms and Dynamic Programming.

Unit 2 · Short notes Bandit Algorithms and Dynamic Programming Multi‑armed bandit algorithms: Upper Confidence Bound (UCB), Probably Approximately Correct (PAC), Median Elimination · Policy gradient methods for bandits · Full reinforcement learning and $MDP$ formulation · Bellman optimality principle · Dynamic programming techniques: value iteration, policy iteration, and policy evaluation · Extensions of DP and convergence analysis using contraction mapping

More for AD-802 (B)

Reinforcement Learning subject page

Other 8th semester AD subjects

All AD 8th semester subjects