LENS Lab

Affiliated with Computer Engineering Systems Group

Texas A&M University

Overview

The Learning and Emerging Networked Systems (LENS) Laboratory at 002 WEB is co-directed by Prof. Srinivas Shakkottai and Prof. Dileep Kalathil. The objectives of the laboratory are to conduct analytical and experimental research in machine learning with networked systems applications, and to facilitate the integration of research into undergraduate and graduate education. The latter objective is directly aimed at enhancing the academic experience of engineering students at Texas A&M University. Key to the success of this program is the current enthusiasm among students for emerging technologies, including distributed learning and control platforms that operate over the network stack.

More about us

We work with different programming environments, including Gymnasium, python packages for machine learning, open source communication stacks such as srsRAN, and OpenFlow for software defined networking (SDN).Hardware support includes GPU workstations from Lambda Labs, Software Defined Radios (SDR) from National Instruments in both sub-six and mm-wave bands, a variety of robots such as Jackal UGVs, Turtlebots and Amazon DeepRacers and assorted Android-based smart devices.We are also supported in conducting real-world field experiments by the Bush Combat Development Complex located at a former Air Force base located about ten miles away from the main campus.Participants are encouraged to act as a community of experts and talk about their experiences with one another. Prototyping often poses many technical challenges. Getting involved at the LENS lab entails being exposed to the frustrations and the rewards associated with open-ended engineering problems.

The lab is supported through the sponsorship of several organizations including Department of Electrical and Computer Engineering at Texas A&M University, National Instruments, Google, the National Science Foundation, and The US Army Futures Command, among others.

Courses Taught by Faculty

ECEN 424 Fundamentals of Networking

ECEN 489 Artificial Intelligence

ECEN 489 Mobile Applications with Android

ECEN 743 Reinforcement Learning

ECEN 750 Design and Analysis of Communication Networks

ECEN 756 Game Theory

News

• [09/2023] TAMU News article about our new NSF grant for the project “Combining Deep Reinforcement Learning Control with Novel Vertical Flight Concepts for Robust Ship based Operation” Link
• [09/2023] TAMU News article about our new ONR grant for the project “EdgeRIC- Empowering Real-time Intelligent Control and Optimization for NextG Cellular Radio Access Networks” Link
• [08/2023] Kishan Panaganti has graduated with a PhD dissertation on “Robust Reinforcement Learning- Theory and Algorithms”! He will join as a Postdoc in Caltech.
• [08/2023] Archana Bura has graduated with a PhD dissertation on “Constrained Reinforcement Learning for Wireless Networks”! She will join as a Postdoc in University of California, San Diego (UCSD).
• [08/2023] Desik Rengarajan has graduated with a PhD dissertation on “Enhancing Reinforcement Learning using Data and Structure”! He will join as a Research Scientist in the HP Labs.

Recent Research

Quickly discover relevant content by filtering publications.

LLMZip: Lossless Text Compression using Large Language Models

We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor …

Chandra Shekhara Kaushik Valmeekam, Krishna Narayanan, Dileep Kalathil, Jean-Francois Chamberland, Srinivas Shakkottai

Federated Ensemble- Directed Offline Reinforcement Learning

We consider the problem of federated offline reinforcement learning (RL), a scenario under which distributed learning agents must …

Desik Rengarajan, Nitin Ragothaman, Dileep Kalathil, Srinivas Shakkottai

DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning

Safe reinforcement learning is extremely challenging–not only must the agent explore an unknown environment, it must do so while …

Archana Bura, Aria HasanzadeZonuzy, Dileep Kalathil, Srinivas Shakkottai, Jean-Francois Chamberland

Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a …

Desik Rengarajan, Sapana Chaudhary, Jaewon Kim, Dileep Kalathil, Srinivas Shakkottai

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

A major challenge in real-world reinforcement learning (RL) is the sparsity of reward feedback. Often, what is available is an …

Desik Rengarajan, Gargi Vaidya, Akshay Sarvesh, Dileep Kalathil, Srinivas Shakkottai

See all publications

Group

List of Students

Current Students
Zaiyan Xu,    PhD ,   Webpage
Sapana Chaudhary,    PhD,    Webpage
Sarat Bobbili ,   PhD
Jeremy Carleton ,   PhD
Ujwal Dinesha ,   PhD
Bhavya Nukapotula ,   PhD
Vicram Rajagopalan,    PhD
Prathik Vijaykumar,    MS,    Webpage

Alumni
Kishan Panaganti,    PhD
Archana Bura,    PhD
Desik Rengarajan,    PhD
Gayathri Narayanan,    MS
Gargi Vaidya,    MS

Lab Gallery

Sneak peek into the lab

Contact

sshakkot@tamu.edu , dileep.kalathil@tamu.edu
1-979-458-0094
188 Bizzell St , Wisenbaker Engineering Building (WEB) - 002, College Station, TX 77840