Hello, I'm Murtaza Rangwala
I am a Ph.D. candidate in Electrical Engineering at Virginia Tech, advised by R. K. Williams, and expect to graduate on December 16, 2026.
My research focuses on reinforcement learning, multi-agent reinforcement learning, and high-throughput research software for learning and robotics.
I created Coordination for Scale RL (casRL), an open-source PyTorch framework that builds RL and MARL experiments from reusable components and runs end-to-end training at 2–4 million environment steps per second on a single node with one CPU and one GPU.
Research and engineering highlights
All projects
Publications
Research overviewIntermittent Deployment for Large-Scale Multi-Robot Forage Perception: Data Synthesis, Prediction, and Planning
Jun Liu, Murtaza Rangwala, Kulbir S. Ahluwalia, Shayan Ghajar, Harnaik S. Dhami, Pratap Tokekar, Benjamin F. Tracy, Ryan K. Williams
IEEE T-ASE, 2024
A data-synthesis, prediction, planning, and intermittent-deployment pipeline for large-scale agricultural robot teams.
DeepPaSTL: Spatio-Temporal Deep Learning Methods for Predicting Long-Term Pasture Terrains Using Synthetic Datasets
Murtaza Rangwala, Jun Liu, Kulbir S. Ahluwalia, Shayan Ghajar, Harnaik S. Dhami, Benjamin F. Tracy, Pratap Tokekar, Ryan K. Williams
Agronomy, 2021
Long-horizon pasture prediction from synthetic spatio-temporal datasets for planning agricultural-robot deployments.
Learning Multi-Agent Communication through Structured Attentive Reasoning
Murtaza Rangwala, Ryan K. Williams
NeurIPS, 2020
A memory-based attention architecture that learns which inter-agent messages matter while reasoning over prior information.
A broader engineering path
Before graduate school, I co-founded an electric-mobility company and worked on electrical, embedded, and vehicle systems at Volvo Trucks.
My earlier engineering work includes leading suspension and brakes for a Formula SAE car that won the SUPRA SAE India skidpad event and captaining the PISat student satellite program as its electrical power-systems lead.