Publications

2025

1. Do as you teach: a multi-teacher approach to self-play in deep reinforcement learning Kharyal, Chaitanya, Gottipati, Sai Krishna, Sinha, Tanmay Kumar, and others, Neural Computing and Applications 2025
2. Human-AI collaboration in real-world complex environment with reinforcement learning Islam, Md Saiful, Das, Srijita, Gottipati, Sai Krishna, and others, Neural Computing and Applications 2025
3. A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs Arabneydi, Jalal, Islam, Saiful, Das, Srijita, Gottipati, Sai Krishna, Duguay, William, Mars, Cloderic, Taylor, Matthew E., Guzdial, Matthew, Fagette, Antoine, and Zerouali, Younes arXiv 2025

2024

1. Generative Active Learning for the Search of Small-molecule Protein Binders Korablyov, Maksym, Liu, Cheng-Hao, Jain, Moksh, Sloot, Almer M., Jolicoeur, Eric, Ruediger, Edward, Nica, Andrei Cristian, Bengio, Emmanuel, Lapchevskyi, Kostiantyn, St-Cyr, Daniel, Schuetz, Doris Alexandra, Butoi, Victor Ion, Rector-Brooks, Jarrid, Blackburn, Simon, Feng, Leo, Nekoei, Hadi, Gottipati, SaiKrishna, Vijayan, Priyesh, Gupta, Prateek, Rampášek, Ladislav, Avancha, Sasikanth, Bacon, Pierre-Luc, Hamilton, William L., Paige, Brooks, Misra, Sanchit, Jastrzebski, Stanislaw Kamil, Kaul, Bharat, Precup, Doina, Hernández-Lobato, José Miguel, Segler, Marwin, Bronstein, Michael, Marinier, Anne, Tyers, Mike, and Bengio, Yoshua arXiv 2024
2. GLIDE-RL: Grounded Language Instruction through DEmonstration in RL Kharyal, Chaitanya, Gottipati, Sai Krishna, Sinha, Tanmay, Das, Srijita, and Taylor, Matthew E. Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems 2024 [Abs]

   A critical capability in the development of complex human-AI collaborative systems is the ability of AI agents to understand the natural language and perform tasks accordingly.

3. Towards Human-Steerable Battery Energy Storage System Optimization: A Novel MDP Framework Gottipati, Sai Krishna, Mars, Clodéric, Gabaud, Julien, Abdollahi, Vahid, Moujtahid, Laila El, and Taylor, Matthew E. Autonomous Agents for Social Good Workshop at AAMAS 2024

2023

1. Hiking up that HILL with Cogment-Verse: Train & Operate Multi-agent Systems Learning from Humans Gottipati, Sai Krishna, Nguyen, Luong-Ha, Mars, Clodéric, and Taylor, Matthew E. Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems 2023 [Abs]

   As more AI systems are deployed, humans are increasingly required to interact with them in multiple settings. However, such AI systems seldom learn from these interactions with humans, which provides an important opportunity to improve from human expertise and context awareness. Several recent results in the fields of reinforcement learning (RL) and human-in-the-loop learning (HILL) show that AI agents can perform better when humans are involved in their training process. Humans can provide rewards to the agent, demonstrate tasks, design curricula, or act directly in the environment, but these potential performance improvements also come with architectural, functional design, and engineering complexities. This paper discusses Cogment, a unifying open-source framework that introduces a formalism to support a variety of human(s)-agent(s) collaboration topologies and training approaches. Cogment addresses the complexity of training with humans within a production-ready platform. On top of Cogment, we introduce Cogment Verse a research platform dedicated to the research community to facilitate the implementation of HILL and Multi-Agent RL experiments. With these platforms, our end goal is to enable the generalization of intelligence ecosystems where AI agents and humans learn from each other and collaborate to address increasingly complex or sensitive use cases. The video demonstration is available at https://youtu.be/v-K0DqIL9K0

2. Human-AI Interactions: A Workshop on Multi-Agent Systems Mars, Clodéric, Gottipati, Sai Krishna, and others, Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023
3. Human-Machine Teaming for UAVs: An Experimentation Platform Moujtahid, Laila El, Gottipati, Sai Krishna, Mars, Clodéric, and Taylor, Matthew E. arXiv 2023
4. Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning Bhati, Rupali, Gottipati, Sai Krishna, Mars, Clodéric, and Taylor, Matthew E. arXiv 2023

2022

2021

1. Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations Redefined, A. I., Gottipati, Sai Krishna, Kurandwad, Sagar, Mars, Clodéric, Szriftgiser, Gregory, and Chabot, François AAMAS Workshop on Multi-Agent Reinforcement Learning 2021
2. Towered Actor Critic For Handling Multiple Action Types In Reinforcement Learning For Drug Discovery Gottipati, Sai Krishna, Pathak, Yashaswi, Sattarov, Boris, Sahir, , Nuttall, Rohan, Amini, Mohammad, Taylor, Matthew E., and Chandar, Sarath Proceedings of the AAAI Conference on Artificial Intelligence 2021

2020

1. Learning to Navigate in Synthetically Accessible Chemical Space Using Reinforcement Learning Gottipati, Sai Krishna, Sattarov, Boris, Niu, Sufeng, Wei, Haoran, Pathak, Yashaswi, Liu, Shengchao, Blackburn, Simon, Thomas, Karam, Coley, Connor, Tang, Jian, Chandar, Sarath, and Bengio, Yoshua Proceedings of Machine Learning and Systems 2020 2020 [Abs]

   Over the last decade, there has been significant progress in the field of machine learning-based de novo drug discovery, particularly in generative modeling of chemical structures. However, current generative approaches exhibit a significant challenge: they do not ensure the synthetic accessibility nor provide the synthetic routes of the proposed small molecules which limits their applicability. In this work, we propose a novel reinforcement learning (RL) setup for drug discovery that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo compound design system. In this setup, the agent learns to navigate through the immense synthetically accessible chemical space by subjecting initial commercially available molecules to valid chemical reactions at every time step of the iterative virtual synthesis process. The proposed environment for drug discovery provides a highly challenging test-bed for RL algorithms owing to the large state space and high-dimensional continuous action space with hierarchical actions. Our end-to-end approach achieves state-of-the-art performance when compared against other generative approaches for drug discovery. Moreover, we leverage our approach in a proof-of-concept that mimics the drug discovery process by generating novel HIV drug candidates. Finally, we describe how the end-to-end training conceptualized in this study represents an important paradigm in radically expanding the synthesizable chemical space and automating the drug discovery process.

2. MapLite: Autonomous Intersection Navigation Without a Detailed Prior Map Ort, T., Murthy, K., Banerjee, R., Gottipati, S. K., Bhatt, D., Gilitschenski, I., Paull, L., and Rus, D. IEEE Robotics and Automation Letters 2020
3. Maximum Reward Formulation In Reinforcement Learning Gottipati, Sai Krishna, Pathak, Yashaswi, Nuttall, Rohan, Sahir, , Chunduru, Raviteja, Touati, Ahmed, Subramanian, Sriram Ganapathi, Taylor, Matthew E., and Chandar, Sarath NeurIPS 2020 Deep RL Workshop 2020

2019

1. Deep Active Localization Gottipati, S. K., Seo, K., Bhatt, D., Mai, V., Murthy, K., and Paull, L. IEEE Robotics and Automation Letters 2019

2018

1. Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting Sai Krishna G, V, Goyette, Kyle, Chamseddine, Ahmad, and Considine, Breandan preprint arXiv:1806.00683 2018

2017

1. Reconstructing vehicles from a single image: Shape priors for road scene understanding Murthy, J. K., Krishna, G. V. S., Chhaya, F., and Krishna, K. M. 2017 IEEE International Conference on Robotics and Automation (ICRA) 2017