Yelchuri Venkata Sai Harsha
I’m Harsha Yelchuri, a robotics researcher. I graduated with a B.E. in Information Science from R.V. College of Engineering. After college, I jumped into research at the Indian Institute of Science. I worked on …
Reinforcement Learning
Vishnu Vinod
I’m a Dual Degree graduate in Computer Science from IIT Madras. During my undergrad and masters I have worked on a wide variety of topics including Adversarial ML, Reinforcement Learning, Differential Privacy, …
PolicyClusterGCN: Identifying Efficient Clusters for Training Graph Convolutional Networks
Graph convolutional networks (GCNs) have achieved huge success in several machine learning (ML) tasks on graph-structured data. Recently, several sampling techniques have been proposed for the efficient training of GCNs …
Adhil Ahmed P M Shums
My name is Adhil Ahmed P M Shums. I have completed my B.E. in Automobile Engineering from MIT, Anna University. I am also doing an online B.S in Data Science and Applications from IIT Madras, in parallel. Apart from …
End-to-end Autonomous Driving in Heterogeneous Traffic Scenario Using Deep Reinforcement Learning
In this paper, we propose an end-to-end autonomous driving architecture for safe maneuvering in heterogeneous traffic using a reinforcement learning (RL) algorithm. Using the proposed architecture we develop an RL agent …
RePReL: a unified framework for integrating relational planning and reinforcement learning for effective abstraction in discrete and continuous domains
Optimizing Traffic Control with Model-Based Learning: A Pessimistic Approach to Data-Efficient Policy Inference
Traffic signal control is an important problem in urban mobility with a significant potential for economic and environmental impact. While there is a growing interest in Reinforcement Learning (RL) for traffic signal …
Physics-Informed Model-Based Reinforcement Learning
We apply reinforcement learning (RL) to physical systems, in particular, robotic systems undergoing rigid body motion without contacts. One of the drawbacks of traditional RL algorithms has been their poor sample …
Devika Jay
I completed my PhD(2021) and MS (2013) from IIT-Madras. Prior to pursuing Phd, I worked with POWERGRID as Deputy Manager.
Evolutionary Approach to Security Games with Signaling
Green Security Games have become a popular way to model scenarios involving the protection of natural resources, such as wildlife. Sensors (e.g. drones equipped with cameras) have also begun to play a role in these …
Improving Sample Efficiency in Evolutionary RL using Off-policy Ranking
--Dr. Gugan Thoppe-- Reinforcement learning is a type of machine learning technique where the agent learns from the interactive environment by trial and error and has applications in sectors such as self-driving cars, …
Causal Contextual Bandits with Targeted Interventions
We study a contextual bandit setting where the learning agent has the ability to perform interventions on targeted subsets of the population, apart from possessing qualitative causal side-information. This novel …
Scalable multi-product inventory control with lead time constraints using reinforcement learning
Smooth Imitation Learning via Smooth Costs and Smooth Policies
Imitation learning (IL) is a popular approach in the continuous control setting as among other reasons it circumvents the problems of reward mis-specification and exploration in reinforcement learning (RL). In IL from …
An Active Learning Framework for Efficient Robust Policy Search
Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a …
CombSGPO: A new algorithm to protect wildlife
Poaching and illegal smuggling of wildlife have remained a cause of concern for wildlife authorities. As per the World Wide Fund for Nature (WWF), Wildlife trade poses the second-biggest direct threat to the survival of …
RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
State abstraction is necessary for better task transfer in complex reinforcement learning environments. Inspired by the benefit of state abstraction in MAXQ and building upon hybrid planner-RL architectures, we propose …
SEERL: Sample Efficient Ensemble Reinforcement Learning
Reinforcement Learning for Unified Allocation and Patrolling in Signaling Games with Uncertainty
An Enhanced Advising Model in Teacher-Student framework using State Categorization
The teacher-student framework aims to improve the sample efficiency of RL algorithms by deploying an advising mechanism in which a teacher helps a student by guiding its exploration. Prior work in this field has …
Human-in-the-loop for Safe and Verifiable Reinforcement Learning
One of the main challenges in implementation of RL in real life applications is safety. Particularly, the undesired and harmful behaviour of RL agents involving humans is one of the major safety concerns. Utilizing the …
Attention Mechanisms in Deep Neural Networks
Recently the Deep Learning community has shown great interest in attention mechanisms to train neural networks – the network pays attention to only certain parts of the input or to certain parts of the network structure …
Learning With Limited Partial and Noisy Data
An area of significant interest in data science is its use on extensively large data sets that are being thrown up due to the changing landscape of computational improvements and IoT. While this addresses a new and …
Chandrashekar Lakshminarayanan
Dr. Chandra Shekar Lakshminarayanan is an Assistant Professor at Department of Computer Science & Engineering, IIT Madras. He obtained his PhD from the Department of Computer Science and Automation, Indian Institute …
Finding Influencers in Social Networks: Reinforcement Learning Shows the Way
Social Network Analysis has given us many tools to effectively manage information dissemination in a social group, study growth and dynamics in such groups, etc. But one of the key challenges when studying social groups …
Returaj Burnwal
I have completed my B.Tech in Electrical Engineering from IIT Hyderabad and was previously working at Yahoo Japan as a Software Engineer. I am currently working on Agent Based modeling of Covid-19 disease spread under …
Chandrasekar Subramanian
Previously Prouct Manager at Microsoft, Prior to that was in Mckinesy, Oliver wyman &TCS R&D. M.Tech (2008) IITM, Ms (2012) Oxford Uk
Sriraam Natarajan
My research interests lie in the fields of Artificial Intelligence and Machine Learning and their application to healthcare problems. More specifically, I am interested in the areas of Relational Learning, Reinforcement …
Balaraman Ravindran
Prof. Ravindran is the head of the Robert Bosch Centre for Data Science and Artificial Intelligence (RBC-DSAI) at IIT Madras and a professor in the Department of Computer Science and Engineering. He is also the …
Safety and Stability Preserving Reinforcement Learning
While reinforcement algorithms have achieved notable successes recently, the use of such approaches in controlling real physical systems is not really prevalent. The primary reason for this is the lack guarantees …
Attention Mechanisms in Deep Neural Networks
Recently the Deep Learning community has shown great interest in attention mechanisms to train neural networks - the network pays attention to only certain parts of the input or to certain parts of the network structure …
Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains
This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains. The problem description and solution are both adapted from a real-world business solution. The …
Dynamic Action Repetition for Deep Reinforcement Learning
EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural …
Dynamic frame skip deep q network
Deep Reinforcement Learning methods have achieved state of the art performance in learning control policies for the games in the Atari 2600 domain. One of the important parameters in the Arcade Learning Environment (ALE) …
An extended reinforcement learning model of basal ganglia to understand the contributions of serotonin and dopamine in risk-based decision making, reward prediction, and punishment learning
Although empirical and neural studies show that serotonin (5HT) plays many functional roles in the brain, prior computational models mostly focus on its role in behavioral inhibition. In this study, we present a model of …