frank47ltt Goto Github PK

aa

assignment1

counterfactual_caps

cpp_project

data-mining-project

Project for Using Machine Learning and Statistic Model to analyze real world dataset, classified into different subtopics

data-structure-algorithm

dqn_assignment_2_frank

frank47ltt.github.io

gc-game-jam

Designed and Implemented a unity-based RPG game

java-projects

maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

marl-anomaly-detect

This project tests multiple different machine learning algorithms that can detect adversarial attacks in multi-agent reinforcement learning settings. Baselines were used to compare performance of a proposed ensemble model. Then, using FGSM, we re-attacked the ensemble detection model with perturbed observations. Read more at the pdf titled FinalPaper.

marl_robustness

This is the code for my first author paper with the research group --- On Weaponizing Actions in Multi-Agent Reinforcement Learning: Theoretical and Empirical Study on Security and Robustness, The 24th International Conference on Principles and Practice of Multi-Agent Systems, 2022, accepted

robustness-of-rl

robustrl-osrl

This code is for our paper: Joe McCalmon; Tongtong Liu; Reid Goldsmith; Andrew Cyhaniuk; Talal Halabi; Sarra Alqahtani, Safe Reinforcement Learning via Observation Shielding, The Hawaii International Conference on System Sciences HICSS2023, accepted.

rollercoasterking

A front end side project

statistical-analysis-with-r