1. CS7.603: Topics in Reinforcement Learning (4 credits, since Spring 23) 

2. MA601: Probability and Statistics (4 credits, since Monsoon 22) 

3. CS3.307: Performance modeling for computer systems (2 credits, since Spring 22)

4.  EE309: Introduction to communication systems (Spring 20, 3 credits, @ IIT Dharwad)

5. EE 216: Communication lab (Spring 20, 3 credits, @ IIT Dharwad)

6. EE 407: Course on Stochastic Processes (Autumn 20, 6 credits, @ IIT Dharwad)

Dual Degree

• Saketh Ayyagari: Model free reinforcement learning for non-stationary environments

• Harshit Lalwani: Reinforcement learning for LDPC/message passing 

• Kavin Aravindan: Kernel selection for Gaussian Processes. 

• Kshitij Mishra: Tabular and Deep Reinforcement learning for Gittins index

• Shikhar Saksena: CGD: Modifying the loss landscape by gradient regularization 

Honors and B.Tech Projects

• Aks Kanodia: Gaussian Processes for dynamic pricing and optimal execution

• Aanvik Bhatnagar: RL for optimal multiple stopping problems

• Mrudani Pimpalkhare: Optimal timing of Systematic Investment Plans

• Manitej Sriram: Kernel selection for Gaussian Processes

• Nishita Kannan:  Merton's Portfolio Optimization

• Shivani Kulkarni: Merton's portfolio theory and Discrete models of Financial Markets

• Shreeprabhas Varma: Optimal timing of Systematic Investment Plans

• Sohan Thummala: Change point detection with MMD

• Sriyansh Suryadevara: RL for optimal multiple stopping problems

Former Students/Projects

• Pranav Agrawal, B.Tech Honors: Reinforcement learning for Dynamic pricing and learning 

• Anush Anand, B.Tech Honors: Bayesian Optimization for dynamic pricing .

• S Akash (Intern, IIT Patna): MAQL: Speeding up Q-learning with a model assist.

• Basab Ghosh (Intern, IISc): Var/Cvar minimization and Risk sensitive RL.

• Sukhjinder Kumar (Intern, IIITH Alumni): Policy gradient for Markovian Bandits.

• Pratham Thakkar & Nipun Tulsian (BTP): Model free reinforcement learning in non-stationary environments.

• Aman Raj (BTP): Data driven estimation in queues.

• Shivam Sood (BTP): Diffusion models for Reinforcement learning.  

• Meka Sai Mukund  (Independent Study) : Surrogate Gradient Descent using GP.

• Anurag Gupta, B.Tech (Independent Study): RL algorithms for dynamic pricing and learning.

•  Kunal Jain, Dual Degree (Independent Study): Bayesian Optimization for Composite functions

• Naman Ahuja, Dual Degree (Independent Study): Topics in Revenue Management and Pricing  

• Rohit Reddy (BTP stage 2): Generative Adversarial Networks for simulating Markov chains.

• Srinath Maddineni (BTP Stage 2): Convergent DQN with Spectral Normalization

• Romaharshan Pusapati, Vamsi Krishna, Sudheer Reddy (BTP Stage 2): Notes on Regret Analysis for Bandits

• Paritosh Pankaj (Intern, IIT Kanpur) : Bayesian Optimization for Dynamic pricing and learning.

• Harshit Dhankhar (Intern, IIT Patna): Tabular and Deep Reinforcement learning for Gittins index.

• Aditya Iyer (Intern, Manipal): Generative Adversarial Networks for simulating random variables. 

• Aryan C. and Kushagra K: First order Bayesian Optimization for RL tasks (R&D project @ IIT Dharwad, co-supervised with Prof. K.J. Prabuchandran) 

• Utkarsh K: Bayesian optimization using the first order (gradient) conditions. (Summer project + BTP @ IIT Dharwad in 2021,  co-supervised with Prof. K.J. Prabuchandran)

• Aryan C. and Kushagra K. : Scheduling in queues with deadline. (Summer project @ IIT Dharwad in 21)

• Venkata D. B. & Deepak N. : Modelling the COVID-19 pandemic: The SAQR model (BTP@ IIT Dharwad in 2020)