Desik Rengarajan — accepted AI-conference papers

2025

Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters

Soumyendu Sarkar, Avisek Naug, Antonio Guillen, Vineet Gundecha, Ricardo Luna Gutiérrez, Sahand Ghorbanpour +4

AAAI 2025technical

Reducing the environmental impact of cloud computing requires efficient workload distribution across geographically dispersed Data Center Clusters (DCCs) and simultaneously optimizing liquid and air (HVAC) cooling with time shift of workloads within individual data centers (DC). This paper introduce…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters

Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Sahand Ghorbanpour, Avisek Naug +3

AAAI 2025technical

We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Learning agent to add minimum distortion to input images while s…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Federated Ensemble-Directed Offline Reinforcement Learning

Desik Rengarajan, Nitin Ragothaman, Dileep Kalathil, Srinivas Shakkottai

NeurIPS 2024poster

We consider the problem of federated offline reinforcement learning (RL), a scenario under which distributed learning agents must collaboratively learn a high-quality control policy only using small pre-collected datasets generated according to different unknown behavior policies. Na\"{i}vely combin…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

SustainDC: Benchmarking for Sustainable Data Center Control

Avisek Naug, Antonio Guillen, Ricardo Luna Gutierrez, Vineet Gundecha, Cullen Bash, Sahand Ghorbanpour +6

NeurIPS 2024poster

Machine learning has driven an exponential increase in computational demand, leading to massive data centers that consume significant amounts of energy and contribute to climate change. This makes sustainable data center control a priority. In this paper, we introduce SustainDC, a set of Python envi…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2022

Enhanced Meta Reinforcement Learning via Demonstrations in Sparse Reward Environments

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

NeurIPS 2022accept

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The meta-policy, when adapted over only a small (or just a single) number of steps, is able to perform near-optimally on a new, related task. However,…

Cited by 2 Source ↗PDF ↗Scholar ↗

2022

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

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

ICLR 2022spotlight

A major challenge in real-world reinforcement learning (RL) is the sparsity of reward feedback. Often, what is available is an intuitive but sparse reward function that only indicates whether the task is completed partially or fully. However, the lack of carefully designed, fine grain feedback imp…

Cited by 83 Source ↗PDF ↗code ↗Scholar ↗

2021

Reinforcement Learning for Mean Field Games with Strategic Complementarities

Kiyeob Lee, Desik Rengarajan, Dileep Kalathil, Srinivas Shakkottai

AISTATS 2021poster

Mean Field Games (MFG) are the class of games with a very large number of agents and the standard equilibrium concept is a Mean Field Equilibrium (MFE). Algorithms for learning MFE in dynamic MFGs are unknown in general. Our focus is on an important subclass that possess a monotonicity property call…

Cited by 18 Source ↗PDF ↗Scholar ↗