Aneesh C. Muppidi

Aneesh Muppidi

I am a Rhodes Scholar and a Harvard undergrad (AB/SM program). At Harvard's Kempner AI institute, I am a KURE fellow advised by Prof. Samuel Gershman. At the Harvard Computational Robotics Lab, I am advised by Prof. Hank Yang. At MIT , I'm advised by Ila Fiete. I was the President of the Harvard Computational Neuroscience Undergraduate Society and Harvard Dharma. I write for the Harvard Crimson. I also like film photography.

How can agents learn in unknown worlds? (read my SOP).

Recent News

I received the US Rhodes Scholarship
My first-author work was accepted to NeurIPS (Poster) Main Conference, and RLC (Spotlight), RSS (Spotlight), and TTIC workshops! Check out the website and code.
Preprint on Particle Filters for Continual DL/RL is out!

Research
	Permutation Invariant Learning with High-Dimensional Particle Filters Akhilan Boopathy, Aneesh Muppidi*, Peggy Yang, Abhiram Iyer, William Yue Ila Fiete equal contribution arXiv, 2024 project page / code / arXiv What is the optimal order of training data? Particle filters can be invariant to training data permutations, mitigiating plasticity loss and catastrophic forgetting.
	Fast TRAC: A Parameter-free Optimizer for Lifelong Reinforcement Learning Aneesh Muppidi, Zhiyu Zhang, Hank Yang NeurIPS, 2024 project page / code / arXiv Mitigate plasticity loss, accelerate forward transfer, and avoid policy collapse with just one line of code.
	Resampling-free Particle Filters in High-dimensions Akhilan Boopathy, Aneesh Muppidi, Peggy Yang, Abhiram Iyer, William Yue Ila Fiete ICRA, 2024 arXiv Particle filters for Pose Estimation.
	Speech Emotion Recognition using Quaternion Convolutional Neural Networks Aneesh Muppidi, Martin Radfar ICASSP, 2021 arXiv QCNNs beat SOTA SER models.

RL Projects
	Let's Learn Agency: Learning Emergent Agent and Non-Agent Trajectory Representations MIT 6.8200 with Pulkit Agrawal Project Report, Video Presentation
	Generating Suboptimal Expert Demonstrations with Large Language Models MIT 6.4212 with Russ Tedrake, project advised by Lirui Wang Project Report, Video Presentation
	Rapid Learning Mechanisms and Neural Representations in Reinforcement Learning Harvard PSY 2350R with Sam Gershman, project advised by Jay Henning Project Report, Code, Research Notebook
	Diffusion Policy for Classical Control Problems Harvard ES158 with Heng Yang Project Report, Code, Slides
	Visualizing Collaborative Multi-Agent Reinforcement Learning Harvard CS271 with Johanna Beyer and Hanspeter Pfister Project Report, Slides

A big thanks to the kind Jon Barron.