AdaptiveStressTesting.jl
AdaptiveStressTesting.jl is a software package written in Julia for stress testing safety-critical systems. The package uses reinforcement learning to search for the highest-probability path from an initially healthy system state to a failure event. The package has been applied to find scenarios of near mid-air collisions (NMACs) in prototypes of the Next-Generation Airborne Collision Avoidance System (ACAS X).
Related Publications:
- Lee, R., Mengshoel, O.J., Saksena, A., Gardner, R., Genin, D., Silbermann, J., Owen, M., Kochenderfer, M.J., “Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning”, Journal of Artificial Intelligence Research, 69, pp.1165-1201, 2020
GBDTs.jl
GBDTs.jl is a software package written in Julia for learning Grammar-Based Decision Trees (GBDTs). GBDT combines decision trees, context-free grammars, and expression optimization for automatically categorizing and explaining data. The package has been applied to categorize scenarios of near mid-air collisions (NMACs) in prototypes of the Next-Generation Airborne Collision Avoidance System (ACAS X).
Related Publications:
- Lee, R., Kochenderfer, M.J., Mengshoel, O.J., Silbermann, J., “Interpretable Categorization of Heterogeneous Time Series Data”, SIAM International Conference on Data Mining, 2018
ExprOptimization.jl
ExprOptimization.jl is a software package written in Julia for the optimization of expression trees. The package can be used to learn expressions or executable source code from input/output examples, also known as “program induction”. The package implements a number of tree optimization algorithms including Genetic Programming, Monte Carlo, and Grammatical Evolution. The software has been used to learn interpretable rules in multivariate heterogeneous time series datasets.
Related Publications:
- Lee, R., Kochenderfer, M.J., Mengshoel, O.J., Silbermann, J., “Interpretable Categorization of Heterogeneous Time Series Data”, SIAM International Conference on Data Mining, 2018
Multi-Fidelity Simulator (MFSim)
MFSim is a fast-time national airspace simulator written in Java. The simulator uses a hierarchical backend that allows aircraft in different regions of the airspace to be simulated at different levels of fidelity. The simulator has been used as a platform for research in multi-agent reinforcement learning of air traffic automation.
Related Publications:
- Agogino, A., Iscen, A., Lee, R., Bowers, D., Tumer, K., Brat, G.P., “Scalable Hierarchical Multifidelity Simulation and Multiagent Optimization of Air Traffic”, AAMAS Workshop on Massive Multiagent Systems, 2015
Network-Form Games Library (libnfg)
Libnfg is a software library written in C++ for implementing Network-Form Games (NFGs). NFGs model systems with multiple human actors whose strategic decisions interact in the context of the system. The algorithms use game theory, probabilistic inference, and reinforcement learning to predict the dynamics of the overall system.
Related Publications:
[bibtex file=RitchieLee.bib key=Lee2012Game,Lee2013Counter,Yan2012,Schlicht2012,Yildiz2012 format=ieee sort=none process_titles=0]
- Lee, R., Wolpert, D.H., “Game Theoretic Modeling of Pilot Behavior During Mid-Air Encounters”, Intelligent Systems Reference Library, 28(4), pp.75-111, Springer, 2012
- Lee, R., Wolpert, D.H., Bono, J., Backhaus, S., Bent, R., Tracey, B., “Counter-Factual Reinforcement Learning: How to Model Decision-Makers That Anticipate the Future”, Decision Making and Imperfection, 474(4), pp.101-128, Springer, 2013
- Yan, G., Lee., R., Kent, A., Wolpert, D.H., “Towards a Bayesian Network Game Framework for Evaluating DDoS Attacks and Defense”, ACM Conference on Computer and Communications Security, 2012
- Schlicht, E., Lee., Wolpert, D.H., Kochenderfer, M.J., Tracey, B., “Predicting the Behavior of Interacting Humans by Fusing Data from Multiple Sources”, Conference on Uncertainty in Artificial Intelligence, 2012
- Yildiz, Y., Lee., R., Brat, G., “Using Game Theoretic Models to Predict Pilot Behavior in NextGen Merging and Landing Scenario”, AIAA SciTech Modeling and Simulation Technologies Conference, 2012