scirs2_optimize/mdp/mod.rs
1//! Markov Decision Process (MDP) solvers
2//!
3//! This module provides exact and approximate MDP solvers including:
4//! - Value Iteration
5//! - Policy Iteration
6//! - Modified Policy Iteration
7//! - Linear Programming approach
8//! - Q-Learning (model-free)
9//! - SARSA (on-policy TD)
10//! - RTDP (Real-Time Dynamic Programming)
11//! - Prioritized Sweeping
12//! - Stochastic Shortest Path
13//! - Inverse Reinforcement Learning (MaxEnt IRL)
14
15pub mod planning;
16pub mod tabular;
17
18pub use planning::*;
19pub use tabular::*;