Algorithms

This section contains examples of different algorithms available in scikit-agent. These examples demonstrate how to use various solution methods, optimization algorithms, and numerical techniques.

The current examples cover neural network training methods following Maliar, Maliar, and Winant (2021). They train networks for several minutes each when the gallery is built from scratch.

Solving a Block Directly (Non-Recurring)

Solving a Block Directly (Non-Recurring)

Training a Policy Network Against a Known Solution

Training a Policy Network Against a Known Solution

The Maliar Training Loop on a Model With No Closed-Form Solution

The Maliar Training Loop on a Model With No Closed-Form Solution

PPO via Stable-Baselines3 on the D-2 Benchmark

PPO via Stable-Baselines3 on the D-2 Benchmark