• Implemented a reinforcement learning (RL) environment for cooperative multi-car team racing using OpenAI Gym

• Experimented with various RL algorithms for training cooperative agents

• Utilized custom reward structures to encourage the emergence of novel behaviors

• Contributed to a research paper discussing emergent team strategies learned by the agents

• Researched novel methods of utilizing Generative Adversarial Networks (GANs) for cybersecurity data generation

• Implemented new GAN architectures in PyTorch in order to facilitate cybersecurity data generation

• Assessed the fidelity of generated cybersecurity data using heuristics gathered from real systems

• Contributed to a research paper discussing the findings of the project