Planning II — MDPs (moved)
This topic reference has been merged into the atomic hub note:
➡️ Markov Decision Process (MDP)
The hub now holds the full reference: formal definition, Markov property, Bellman equation + optimality, Grid World walkthrough, all 6 algorithm pseudocodes (Policy Evaluation, Policy Improvement, Policy Iteration, Value Iteration, Modified PI, Linear Programming), exam traps and comparison tables.
Companion files: