Search Results for author: Venkat Krovi

Found 5 papers, 1 papers with code

A Scalable and Parallelizable Digital Twin Framework for Sustainable Sim2Real Transition of Multi-Agent Reinforcement Learning Systems

no code implementations16 Mar 2024 Chinmay Vilas Samak, Tanmay Vilas Samak, Venkat Krovi

We introduce AutoDRIVE Ecosystem as an enabling digital twin framework to train, deploy, and transfer cooperative as well as competitive multi-agent reinforcement learning policies from simulation to reality.

Multi-agent Reinforcement Learning reinforcement-learning

An Overview of Automated Vehicle Platooning Strategies

no code implementations8 Mar 2024 M Sabbir Salek, Mugdha Basu Thakur, Pardha Sai Krishna Ala, Mashrur Chowdhury, Matthias Schmid, Pamela Murray-Tuite, Sakib Mahmud Khan, Venkat Krovi

Automated vehicle (AV) platooning has the potential to improve the safety, operational, and energy efficiency of surface transportation systems by limiting or eliminating human involvement in the driving tasks.

Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem

no code implementations18 Sep 2023 Tanmay Vilas Samak, Chinmay Vilas Samak, Venkat Krovi

This work presents a modular and parallelizable multi-agent deep reinforcement learning framework for imbibing cooperative as well as competitive behaviors within autonomous vehicles.

Autonomous Vehicles Multi-agent Reinforcement Learning +1

Contrastive Representation Disentanglement for Clustering

no code implementations8 Jun 2023 Fei Ding, Dan Zhang, Yin Yang, Venkat Krovi, Feng Luo

We conduct a theoretical analysis of the proposed loss and highlight how it assigns different weights to negative samples during the process of disentangling the feature representation.

Clustering Contrastive Learning +2

Multi-level Knowledge Distillation via Knowledge Alignment and Correlation

1 code implementation1 Dec 2020 Fei Ding, Yin Yang, Hongxin Hu, Venkat Krovi, Feng Luo

While it is important to transfer the full knowledge from teacher to student, we introduce the Multi-level Knowledge Distillation (MLKD) by effectively considering both knowledge alignment and correlation.

Contrastive Learning Knowledge Distillation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.