I am an Associate Professor in the Department of Computer Science and Engineering, Indian Institute of Technology Bombay. I specialise in artificial intelligence. Driven by the goal of creating intelligent agents—especially ones that can learn—I consider questions in areas such as sequential decision making, multiagent learning, multi-armed bandits, and humanoid robotics. Application domains include robot soccer, computer games, and on-line advertising.

Here is a copy of my CV.

I do not have positions for internships and research projects open to students outside IIT Bombay. I apologise for not being able to respond individually to the numerous queries I receive in this regard.

This semester (Spring 2025), I teach CS 747: Foundations of Intelligent and Learning Agents.

Teaching

• Spring 2024: CS 101: Computer Programming and Utilization
  Autumn 2023: CS 747: Foundations of Intelligent and Learning Agents
  Spring 2023: CS 748: Advances in Intelligent and Learning Agents
  Spring 2023: Mathematical Foundations of Artificial Intelligence and Machine Learning. (NCM-CEP course.)
  Autumn 2022: CS 747: Foundations of Intelligent and Learning Agents
  Spring 2022: CS 748: Advances in Intelligent and Learning Agents (On-line course; lectures, assignments included.)
  Autumn 2021: CS 747: Foundations of Intelligent and Learning Agents (On-line course; lectures, assignments included.)
  Spring 2021: CS 748: Advances in Intelligent and Learning Agents (On-line course; lectures, assignments included.)
  Autumn 2020: CS 747: Foundations of Intelligent and Learning Agents (On-line course; lectures, assignments included.)
  Spring 2020: CS 748: Advances in Intelligent and Learning Agents
  Autumn 2019: CS 747: Foundations of Intelligent and Learning Agents
  Spring 2019: CS 337 and 335: Artificial Intelligence and Machine Learning
  Autumn 2018: CS 747: Foundations of Intelligent and Learning Agents
  Spring 2018: CS 344 and 386: Artificial Intelligence
  Autumn 2017: CS 747: Foundations of Intelligent and Learning Agents
  Spring 2017: CS 344 and 386: Artificial Intelligence
  Autumn 2016: CS 747: Foundations of Intelligent and Learning Agents
  Spring 2016: CS 748: Advances in Intelligent and Learning Agents
  Autumn 2015: CS 747: Foundations of Intelligent and Learning Agents
  

Publications

Journals

• Direction-Changing Fall Control of Humanoid Robots: Theory and Experiments
  Ambarish Goswami, Seung-kook Yun, Umashankar Nagarajan, Sung-Hee Lee, KangKang Yin, and Shivaram Kalyanakrishnan, 2014
  Autonomous Robots.
  [PDF  BibTeX]
  
• Characterizing Reinforcement Learning Methods through Parameterized Learning Problems
  Shivaram Kalyanakrishnan and Peter Stone, 2011
  Machine Learning.
  [PDF  BibTeX   Publisher's on-line version  Notes]
  
• Learning to Predict Humanoid Fall
  Shivaram Kalyanakrishnan and Ambarish Goswami, 2011
  International Journal of Humanoid Robotics.
  [PDF  BibTeX  Publisher's on-line version]
  Electronic version of an article published as: International Journal of Humanoid Robotics, Volume 8, Number 2, pp. 245-273, DOI: 10.1142/S0219843611002496, © copyright World Scientific Publishing Company.
  

Conferences

• Linear-Time Optimal Deadlock Detection for Efficient Scheduling in Multi-Track Railway Networks
  Hastyn Doshi, Ayush Tripathi, Keshav Agarwal, Harshad Khadilkar, and Shivaram Kalyanakrishnan, 2024.
  IJCAI 2024. To appear.
  [PDF  BibTeX]
  This paper was also invited to be presented at the AI for Critical Infrastructure Workshop at IJCAI 2024, Jeju, Korea
  
• Optimal Stopping Rules for Best Arm Identification in Stochastic Bandits under Uniform Sampling
  Vedang Gupta, Yash Gadhia, Shivaram Kalyanakrishnan, and Nikhil Karamchandani, 2024.
  ISIT 2024. To appear.
  [PDF  BibTeX]
  
• PAC Mode Estimation using PPR Martingale Confidence Sequences
  Shubham Anand Jain, Rohan Shah, Sanit Gupta, Denil Mehta, Inderjeet Nair, Jian Vora, Sushil Khyalia, Sourav Das, Vinay J. Ribeiro, and Shivaram Kalyanakrishnan, 2022.
  AISTATS 2022.
  [PDF  BibTeX]
  
• Optimising a Real-time Scheduler for Indian Railway Lines by Policy Search
  Rohit Prasad, Harshad Khadilkar, and Shivaram Kalyanakrishnan, 2021
  ICC 2021.
  [PDF  BibTeX]
  
• Intelligent and Learning Agents: Four Investigations
  Shivaram Kalyanakrishnan, 2021
  IJCAI 2021.
  [PDF  BibTeX]
  
• Lower Bounds for Policy Iteration on Multi-action MDPs
  Kumar Ashutosh, Sarthak Consul, Bhishma Dedhia, Parthasarathi Khirwadkar, Sahil Shah, and Shivaram Kalyanakrishnan, 2020
  CDC 2020.
  [PDF  BibTeX]
  
• Regret Minimisation in Multi-Armed Bandits Using Bounded Arm Memory
  Arghya Roy Chaudhuri and Shivaram Kalyanakrishnan, 2020
  AAAI 2020.
  [PDF  BibTeX]
  
• A Tighter Analysis of Randomised Policy Iteration
  Meet Taraviya and Shivaram Kalyanakrishnan, 2019
  UAI 2019.
  [PDF  BibTeX]
  
• PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits
  Arghya Roy Chaudhuri and Shivaram Kalyanakrishnan, 2019
  ICML 2019.
  [PDF  BibTeX]
  
• Quantile-Regret Minimisation in Infinitely Many-Armed Bandits
  Arghya Roy Chaudhuri and Shivaram Kalyanakrishnan, 2018
  UAI 2018.
  [PDF  BibTeX]
  
• Opportunities and Challenges for Artificial Intelligence in India
  Shivaram Kalyanakrishnan, Rahul Alex Panicker, Sarayu Natarajan, and Shreya Rao, 2018
  AIES 2018.
  [PDF  BibTeX]
  
• Improved Strong Worst-case Upper Bounds for MDP Planning
  Anchit Gupta and Shivaram Kalyanakrishnan, 2017
  IJCAI 2017.
  [PDF  BibTeX]
  
• PAC Identification of a Bandit Arm Relative to a Reward Quantile
  Arghya Roy Chaudhuri and Shivaram Kalyanakrishnan, 2017
  AAAI 2017.
  [PDF  BibTeX]
  
• Batch-Switching Policy Iteration
  Shivaram Kalyanakrishnan, Utkarsh Mall, and Ritish Goyal, 2016
  IJCAI 2016.
  [PDF  BibTeX]
  
• Randomised Procedures for Initialising and Switching Actions in Policy Iteration
  Shivaram Kalyanakrishnan, Neeldhara Misra, and Aditya Gopalan, 2016
  AAAI 2016.
  [PDF  BibTeX  Notes]
  
• On Building Decision Trees from Large-scale Data in Applications of On-line Advertising
  Shivaram Kalyanakrishnan, Deepthi Singh, and Ravi Kant, 2014
  CIKM 2014.
  [PDF  BibTeX]
  
• GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare
  Arpit Agarwal, Harikrishna Narasimhan, Shivaram Kalyanakrishnan, and Shivani Agarwal, 2014
  ICML 2014.
  [PDF  BibTeX]
  
• Information Complexity in Bandit Subset Selection
  Emilie Kaufmann and Shivaram Kalyanakrishnan, 2013
  COLT 2013.
  [PDF  BibTeX  Notes]
  A short version of this paper was presented at the 8èmes Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2013), Lille, France.
  
• PAC Subset Selection in Stochastic Multi-armed Bandits
  Shivaram Kalyanakrishnan, Ambuj Tewari, Peter Auer, and Peter Stone, 2012
  ICML 2012.
  [PDF  BibTeX]
  
• UT Austin Villa 2011: A Champion Agent in the RoboCup 3D Soccer Simulation Competition
  Patrick MacAlpine, Daniel Urieli, Samuel Barrett, Shivaram Kalyanakrishnan, Francisco Barrera, Adrian Lopez-Mobilia, Nicolae Ştiurcă, Victor Vu, and Peter Stone, 2012
  AAMAS 2012.
  [PDF  BibTeX  Supplementary page]
  
• On Optimizing Interdependent Skills: A Case Study in Simulated 3D Humanoid Robot Soccer
  Daniel Urieli, Patrick MacAlpine, Shivaram Kalyanakrishnan, Yinon Bentor, and Peter Stone, 2011
  AAMAS 2011.
  [PDF  BibTeX  Supplementary page]
  A similar version of this paper was presented at The Fifth Workshop on Humanoid Soccer Robots at Humanoids 2010, Nashville, TN, U.S.A.
  
• Efficient Selection of Multiple Bandit Arms: Theory and Practice
  Shivaram Kalyanakrishnan and Peter Stone, 2010
  ICML 2010.
  [PDF  BibTeX  Notes]
  
• Predicting Falls of a Humanoid Robot through Machine Learning
  Shivaram Kalyanakrishnan and Ambarish Goswami, 2010
  IAAI 2010.
  [PDF  BibTeX]
  
• An Empirical Analysis of Value Function-Based and Policy Search Reinforcement Learning
  Shivaram Kalyanakrishnan and Peter Stone, 2009
  AAMAS 2009.
  [PDF  BibTeX]
  
• Batch Reinforcement Learning in a Complex Domain
  Shivaram Kalyanakrishnan and Peter Stone, 2007
  AAMAS 2007.
  [PDF  BibTeX  Notes]
  Nominee for Best Student Paper Award at AAMAS 2007, Honolulu, Hawai'i, U.S.A.
  

Workshops and Symposia

• Half Field Offense: An Environment for Multiagent Learning and Ad Hoc Teamwork
  Matthew Hausknecht, Prannoy Mupparaju, Sandeep Subramanian, Shivaram Kalyanakrishnan, and Peter Stone, 2016
  Adaptive and Learning Agents Workshop 2016.
  [PDF  BibTeX]
  
• On Learning with Imperfect Representations
  Shivaram Kalyanakrishnan and Peter Stone, 2011
  ADPRL 2011.
  [PDF  BibTeX]
  
• Three Humanoid Soccer Platforms: Comparison and Synthesis
  Shivaram Kalyanakrishnan, Todd Hester, Michael Quinlan, Yinon Bentor, and Peter Stone, 2010
  RoboCup 2009. Short paper.
  [PDF  BibTeX]
  
• Learning Complementary Multiagent Behaviors: A Case Study
  Shivaram Kalyanakrishnan and Peter Stone, 2010
  RoboCup 2009.
  [PDF  BibTeX   Supplementary page]
  Winner of Best Student Paper Award at the RoboCup International Symposium 2009, Graz, Austria. A similar version of this paper was presented at the Adaptive and Learning Agents Workshop at AAMAS 2009, Budapest, Hungary. A short version appears in the proceedings of AAMAS 2009.
  
• Integrating Value Function-Based and Policy Search Methods for Sequential Decision Making
  Shivaram Kalyanakrishnan and Peter Stone, 2009
  MSRL 2009. Extended abstract.
  
• Model-based Reinforcement Learning in a Complex Domain
  Shivaram Kalyanakrishnan, Peter Stone, and Yaxin Liu, 2008
  RoboCup 2007.
  [PDF  BibTeX]
  
• Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study
  Shivaram Kalyanakrishnan, Yaxin Liu, and Peter Stone, 2007
  RoboCup 2006.
  [PDF  BibTeX  Supplementary page]
  Winner of Best Student Paper Award at the RoboCup International Symposium 2006, Bremen, Germany.
  

Technical Reports

• An Analysis of Frame-skipping in Reinforcement Learning
  Shivaram Kalyanakrishnan, Siddharth Aravindan, Vishwajeet Bagdawat, Varun Bhatt, Harshith Goka, Archit Gupta, Kalpesh Krishna, Vihari Piratla, 2021.
  [PDF  BibTeX]
  
• Artificial Intelligence and Life in 2030
  Peter Stone, Rodney Brooks, Erik Brynjolfsson, Ryan Calo, Oren Etzioni, Greg Hager, Julia Hirschberg, Shivaram Kalyanakrishnan, Ece Kamar, Sarit Kraus, Kevin Leyton-Brown, David Parkes, William Press, AnnaLee Saxenian, Julie Shah, Milind Tambe, and Astro Teller, 2016
  One Hundred Year Study on Artificial Intelligence: Report of the 2015-2016 Study Panel, Stanford University, Stanford, CA, September 2016.
  [PDF  BibTeX  AI100]
  
• UT Austin Villa 2011 3D Simulation Team Report
  Patrick MacAlpine, Daniel Urieli, Samuel Barrett, Shivaram Kalyanakrishnan, Francisco Barrera, Adrian Lopez-Mobilia, Nicolae Ştiurcă, Victor Vu, and Peter Stone, 2011
  Technical Report AI11-10, The University of Texas at Austin, Department of Computer Science, AI Laboratory.
  [PDF  BibTeX  Supplementary page]
  
• Learning Methods for Sequential Decision Making with Imperfect Representations
  Shivaram Kalyanakrishnan, 2011
  Ph.D. dissertation, published as UT Austin Computer Science Technical Report TR-11-41.
  [PDF  BibTeX  Notes]
  
• The UT Austin Villa 3D Simulation Soccer Team 2008
  Shivaram Kalyanakrishnan, Yinon Bentor, and Peter Stone, 2009
  Technical Report AI09-01, The University of Texas at Austin, Department of Computer Science, AI Laboratory.
  [PDF  BibTeX  Supplementary page]
  
• The UT Austin Villa 3D Simulation Soccer Team 2007
  Shivaram Kalyanakrishnan and Peter Stone, 2007
  Technical Report AI07-348, The University of Texas at Austin, Department of Computer Science, AI Laboratory.
  [PDF  BibTeX  Supplementary page]
  

Patents

• Machine Learning Approach for Predicting Humanoid Robot Fall
  Ambarish Goswami and Shivaram Kalyanakrishnan, 2013
  US Patent 8,554,370, issued October 8, 2013.
  

Resources

• SynTalk episode on The Learnable And Not.
• IJCAI 2017 tutorial on the Theoretical Analysis of Policy Iteration.
• Half Field Offense.

Contact Information