Admissible Policy

Average Infinite Horizon Optimization

Belief MDP

Bellman's Optimality Principle

Blackwell's Irrelevant Information Theorem

Bounded-Lipschitz

Controllability & Observability w.r.t. Riccati

Controlled Markov Chain

Discounted Cost

Discounted Infinite Horizon Optimization

Extended Kalman Filter

Filter Stability

Finite Horizon Optimization

Kalman Filter

Linear Quadratic Problem

Markov Decision Process

Markov Policy

Markov Policy induces Markov Chain

Markov Policy is Good Enough

Measurable Selection Conditions

Near Optimal

Optimal

Optimality of Q Learning Algorithm

Partially Observable Markov Decision Process

Policy

Policy Relationships

Polish space

Q-Learning

Riccati Equation

Stationary Policy

Total Variation

Value Iteration Algorithm

Wasserstein Convergence

Wasserstein distance metrizes Wasserstein space

Wasserstein metric

Wasserstein space

Weak convergence

Weak convergence in Wasserstein space

ε-Optimal