readapt 0.1.2

A reinforcement learning library
1
2
3
4
5
6
7
8
9
10
11

//!
//! `readapt` is a collection of algorithms for performing reinforcement.
//!
//! > The term *readapt* signifies an artificial agent caught in a continuous cycle of learning
//! > and relearning — persistently stuck in a time loop where it strives to break free by failing
//! > and adapting through repeated attempts to achieve a goal.

/// Stochastic bandits algorithms
pub mod bandits;
/// Markov decision processes
pub mod mdp;