rlrom 0.1.0

RLROM is a library for testing and training reinforcement learning agent using online monitoring of signal temporal logics formulas, and more.

RLRom

This module integrates Robust Online Monitoring methods with Reinforcement Learning stuff. The motivation is first to test RL agents using interpretable monitors, then use these monitors to train models to perform complex tasks, and/or converge toward behaviors that reliably satisfy certain requirements.

Install

Those are needed for building some of the required python modules, in particular stlrom for STL monitoring.

• CMake
• swig

Then installing should be as simple as

pip install rlrom 

Getting Started

RLRom reads configuration files in the YAML format as inputs. Examples are provided in the examples folder. A command line interface is provided through the script rlrom_run. For instance,

$ rlrom_run test examples/cartpole/cfg_cartpole.cfg

will run a few episode of the cartpole classic environment, fetching a model on huggingface and monitor a formula on these episodes.

More programmatic features are demonstrated in notebooks, in particular this notebook which presents a case study around highway-env environment.