Markov Decision Processes

Understands that an agent acts in an environment, receives rewards, and aims to maximise cumulative return.

Defines MDP formally; solves small MDPs with value iteration and policy iteration.

Applies Bellman equations; understands discount factor, reward shaping, and partial observability (POMDP basics).

Analyses convergence of DP methods; derives TD learning; understands multi-agent MDPs and hierarchical RL.

Contributes to RL theory, safe RL, or multi-agent systems.