Dilip Arumugam

Welcome

I am a fifth-year Ph.D. candidate in the Stanford University Computer Science Department, advised by Benjamin Van Roy. My research is broadly focused on reinforcement learning. In the past, I have completed internships at Microsoft Research Cambridge, Mila, Microsoft Research Redmond, and DeepMind.

I completed my Bachelor's and Master's degrees in the Brown University Computer Science Department. My time at Brown centered around work in reinforcement learning, under my advisor Michael Littman. In parallel, I was a member of the Humans to Robots Laboratory where I worked with Stefanie Tellex on natural language understanding for robots. I was also a member of the Brown Laboratory for Linguistic Information Processing run by Eugene Charniak.

Research Interests

I'm primarily interested in the area of reinforcement learning with the goal of building sequential decision-making agents that learn as efficiently and as remarkably as people do. These days, I'm especially interested in how information theory might offer principled and practical insights into addressing the challenges of sample-efficient reinforcement learning. Other areas of active interest include reinforcement learning with natural language and hierarchical reinforcement learning.

Selected Papers & Publications

For my CV, please click here and, for a complete list of papers, please check Google Scholar, DBLP, or Semantic Scholar (depending on what you're after, one of these may be more reliable than the others).

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

Dilip Arumugam & Benjamin Van Roy.
Advances in Neural Information Processing Systems (NeurIPS), 2022.
ICML Workshop on Decision Awareness in Reinforcement Learning, 2022.
Early version: Multi-disciplinary Conference on Reinforcement Learning & Decision Making (RLDM), 2022.

Planning to the Information Horizon of Bayes-Adaptive Markov Decision Processes via Epistemic State Abstraction

Dilip Arumugam & Satinder Singh.
Advances in Neural Information Processing Systems (NeurIPS), 2022.
Early version: NeurIPS Workshop on Ecological Theory of Reinforcement Learning, 2021.

The Value of Information When Deciding What to Learn

Dilip Arumugam & Benjamin Van Roy.
Advances in Neural Information Processing Systems (NeurIPS), 2021.

Bad-Policy Density: A Measure of Reinforcement Learning Hardness

David Abel, Cameron Allen, Dilip Arumugam, D. Ellis Hershkowitz, Michael L. Littman, Lawson L.S. Wong.
ICML Workshop on Reinforcement Learning Theory, 2021.

Deciding What to Learn: A Rate-Distortion Approach

Dilip Arumugam & Benjamin Van Roy.
International Conference on Machine Learning (ICML), 2021.

An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning

Dilip Arumugam, Peter Henderson, Pierre-Luc Bacon.
NeurIPS Workshop on Biological and Artificial Reinforcement Learning, 2020.

Randomized Value Functions via Posterior State-Abstraction Sampling

Dilip Arumugam & Benjamin Van Roy.
NeurIPS Workshop on Biological and Artificial Reinforcement Learning, 2020.

Value Preserving State-Action Abstractions

David Abel, Nate Umbanhowar, Khimya Khetarpal, Dilip Arumugam, Doina Precup, Michael L. Littman.
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
Multi-disciplinary Conference on Reinforcement Learning & Decision Making (RLDM), 2019.
Early version: ICLR Workshop on Structures and Priors in Reinforcement Learning, 2019.