Logan Mondal Bhamidipaty (罗根)

I'm a Stanford student pursuing a BS in math and an MS in CS (AI focus). I work in Chelsea Finn's IRIS lab on alignment, meta-RL, and POMDPs. Previously, I researched market design with Paul Milgrom (Department of Economics) and dynamical systems with Kwabena Boahen (Brains in Silicon).

I am broadly interested in the confluence of RL and economics. In particular, I want to build RL tools that allow autonomous agents to behave strategically in complex, real-world environments.

Email  /  GitHub  /  CV  /  Google Scholar

profile photo


project image

Scaling Contrastive Preference Learning for Vision Language Models (WIP)

Rafael Rafailov*, Logan Mondal Bhamidipaty*, Joey Hejna, Chelsea Finn

Contrastive preference learning (CPL) is an extension of direct preference optimization (DPO) for arbitrary MDPs that has achieved promising results at small scales. Our project shows that CPL scales elegantly to high-dimensional, multimodal architectures and provides a simple, efficient method for aligning and steering autonomous agents.

project image

Generalizing Meta-RL Methods for POMDPs (WIP)

Annie Xie*, Logan Mondal Bhamidipaty*, Evan Liu, Sergey Levine, Chelsea Finn

Standard exploration methods typically rely on random coverage of the state space or coverage-promoting exploration bonuses. However, in partially observed settings, the biggest exploration challenge is often posed by the need to discover information-gathering strategies – e.g., an agent that has to navigate to a location in traffic might learn to first check traffic conditions and then choose a route. In this work, we design a POMDP agent that gathers information about the hidden state, using ideas from the meta-exploration literature.

project image

DynaDojo: An Extensible Platform for Benchmarking Scaling in Dynamical System Identification

Logan Mondal Bhamidipaty*, Tommy Bruzzese*, Caryn Tran*, Rami Mrad, Maxinder S. Kanwal
NeurIPS (2023)
[paper] [code] [poster]

DynaDojo is a novel Python platform for developing and benchmarking data-driven dynamical systems identification algorithms. It prioritizes resource-efficient parallelization strategies for running on clusters and provides 7 baseline algorithms, 20 dynamical systems, and 3 benchmarking challenges off the shelf, with users easily able to add more.


project image

Market Design Course Reader

Logan Mondal Bhamidipaty*, Paul Milgrom*, Ellie Morgan Tyger, Lea Nagel

The reader focuses on three areas: (1) the design of matching algorithms to solve assignment problems, with applications to school choice, housing markets, and kidney exchanges; (2) the design of auctions to solve general resource allocation problems, with applications to the sale of natural resources, financial assets, radio spectrum, and advertising; and (3) the design of platforms and exchanges, with applications to internet markets. It emphasizes connecting economic theory to practical applications.

website template