[UG/MS/PhD] Seeking CS Student Workers at ICT for Grant Funded Project

The USC Institute for Creative Technologies (ICT) is seeking two (2) student workers to join the Human-inspired Adaptive Teaming Systems (HATS) research team to help us investigate research problem sets related to multi-agent reinforcement learning.

We’re looking for a motivated and detail-oriented student worker to join our team, focusing on leveraging Generative Artificial Intelligence for Scenario Generation. Multi-agent reinforcement learning (MARL) is increasingly used in military training to build dynamic and adaptive synthetic characters for interactive simulations. The effectiveness of MARL algorithms heavily relies on the quality of the scenarios utilized in machine learning experiments.  Our research addresses this challenge by building a scenario generation capability leveraging generative transformer models to generate machine-learning-friendly simulation scenarios based on effective prompts and a data bank of training content (text and images) associated with a capability. Student research assistants will contribute to this research by running scenario generation experiments and assessing the value of generated scenarios in MARL. Strong proficiency in Python and experience with multimodal LLMs (MLLMs) are required. Familiarity with RL concepts is preferred. Knowledge and experience with diffusion based models is a plus.

We’re looking for a motivated and detail-oriented student worker to join our team, focusing on cutting-edge Preference-Driven Multi-Objective Reinforcement Learning research. This role is ideal for a student with a strong interest in reinforcement learning (RL), graph-based systems, and multi-objective optimization. You’ll contribute to a project where multiobjective RL techniques will be first applied to a test set and then to virtual simulation environments.  Strong proficiency in Python and experience with relevant machine learning libraries are required. Familiarity with RL concepts and a solid understanding of key multi-objective optimization concepts, such as Pareto Fronts, non-dominated solutions, and scalarization methods (e.g., weighted sum, Tchebycheff) are preferred. Knowledge of graph-based data structures and an interest in graph neural networks (GNNs) is a plus.