Welcome

Students and faculty affiliated with the THINC lab conduct cutting edge research in AI and Robotics. We rigorously investigate various problems of interest in contexts such as multiagent systems, reinforcement learning, modile robots, and the semantic web. We have published more than a hundred papers in top tier research conferences such as AAAI, UCAI, AAMAS, IROS, ICRA, and journals such as JAIR and JAAMAS. Our research is often multi-disciplinary and we collaborate with renowned researchers including psychologists, education specialists and biologists in the US and beyond. Our research has been funded by grants from NSF, multiple DoD agencies, NIH, and the industry.

DR. PRASHANT DOSHI

Director, THINC Lab

Papers in Preprint

2024

Ryan Grant, Adam Goodie, Prashant Doshi, "The Human-Machine Teammate Inventory (HMTI): Scale Development and Validation", in PsyArXiv [Paper]

2023

Keyang He, Prashant Doshi, Bikramjit Banerjee, "Latent Interactive A2C for Improved RL in Open Many-Agent Systems", in arXiv:2305.05159 [Paper]

Latest Publications

2024

Aditya Shinde, Prashant Doshi, "Modeling Cognitive Biases in Decision-Theoretic Planning for Active Cyber Deception", in AAMAS Conference [Paper]

2023

Keyang He, Prashant Doshi, Bikramjit Banerjee, "Modeling and Reinforcement Learning in Partially Observable Many-Agent Systems", in Journal of Autonomous Agents and Multi-Agent Systems

2023

Ehsan Asali, Prashant Doshi, Jin Sun, "Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation", in Workshop on Reliable and Deployable Learning Based Robotic Systems, CoRL [Paper] [Presentation]

2023

Adam Eck, Leen-Kiat Soh, Prashant Doshi, "Decision Making in Open Agent Systems", in AI Magazine [Paper] [Presentation]

2023

Hannah Tawashy, Prashant Doshi, "Recurrent Sum-Product-Max Networks for Multi-Agent Decision Making: A Perspective", in MSDM 2023: 11th Workshop on Multi-Agent Sequential Decision-Making Under Uncertainty (MSDM), AAMAS [Paper] [Presentation]

2023

Prasanth Sengadu Suresh, Yikang Gui, Prashant Doshi, "Dec-AIRL: Decentralized Adversarial IRL for Human-Robot Teaming", in Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) [Paper] [Presentation]

2022

Saurabh Arora, Bikramjit Banerjee, Prashant Doshi, "Online Inverse Reinforcement Learning with Learned Observation Model", in Conference on Robot Learning (CoRL) [Paper] [Supplement]

2022

Swaraj Pawar, Prashant Doshi, "Anytime Learning of Sum-Product and Sum-Product-Max Networks", in International Conference on Probabilistic Graphical Models (PGM) [Paper] [Supplement] [Presentation]

See More

Latest News

01/01/2024 Prof. Doshi is elected to AAAI's Senior Member status for significant contributions to agent-based decision making in multiagent settings.

12/21/2023 Prof. Doshi visits Shenzhen University and gives an invited seminar on Decision Making in Open Agent Systems at SZU.

10/13/2023 THINC Lab researchers and startup partner InversAI undertook a field visit to A&M Farms in the Vidalia region for on-site R&D of robotic produce processing.

10/05/2023 THINC Lab hosted Prof. Pascal Poupart from University of Waterloo who gave a colloquium on inverse constraint learning and held research discussions with lab members across two days.

08/08/2023 Supported by a new 4-year NSF Medium grant, Prof. Doshi is leading a collaboration with UNL and Oberlin College to model and investigate methods for planning and learning in open multi-agent systems.

See More

Our Team