POMDPStressTesting.jl is a package that uses reinforcement learning and stochastic optimization to find likely failures in black-box systems through a technique called adaptive stress testing. Adaptive stress testing (AST) has been used to find failures in safety-critical systems such as aircraft collision avoidance systems, flight management systems, and autonomous vehicles. The POMDPStressTesting.jl package is written in Julia and is part of the wider POMDPs.jl ecosystem, which provides access to simulation tools, policies, visualizations, and—most importantly—solvers. We provide different solver variants including online planning algorithms such as Monte Carlo tree search and deep reinforcement learning algorithms such as trust region policy optimization (TRPO) and proximal policy optimization (PPO). Stochastic optimization solvers such as the cross-entropy method are also available and random search is provided as a baseline. Additional solvers can easily be added by adhering to the POMDPs.jl interface.

Keywords for this software

Anything in here will be replaced on browsers that support the canvas element

References in zbMATH (referenced in 1 article , 1 standard article )

Showing result 1 of 1.
Sorted by year (citations)

  1. Robert J. Moss: POMDPStressTesting.jl: Adaptive Stress Testing for Black-Box Systems (2021) not zbMATH