Publications

Search
Author Title Type [ Year(Desc)]
2015
Subramanian, S. Ganapathi, & P, A. Ganesh. (2015). Spatial Decision Support System for Industrial Robots. In Innovations in Marine Electrical and Electronics Engineering. Retrieved from https://uwaterloo.ca/scholar/sites/ca.scholar/files/s2ganapa/files/paper29.pdf
2017
Subramanian, S. Ganapathi, & Crowley, M. . (2017). Learning Forest Wildfire Dynamics from Satellite Images using Reinforcement Learning. In Conference on Reinforcement Learning and Decision Making (pp. 244-248). Retrieved from http://www.princeton.edu/~ndaw/RLDM17ExtendedAbstracts.pdf
2018
Subramanian, S. Ganapathi, & Crowley, M. . (2018). A Complementary Approach to Improve WildFire Prediction Systems. In Neural Information Processing Systems (AI for social good workshop). Retrieved from https://aiforsocialgood.github.io/2018/pdfs/track1/37_aisg_neurips2018.pdf
Subramanian, S. Ganapathi. (2018). Reinforcement Learning for Determining Spread Dynamics of Spatially Spreading Processes with Emphasis on Forest Fires. Electrical and Computer Engineering, University of Waterloo. Retrieved from http://hdl.handle.net/10012/13148
Subramanian, S. Ganapathi, Ghojogh, B. , Sambee, J. Singh, & Crowley, M. . (2018). Decision Assist For Self-Driving Cars. In 31st Canadian Conference on Artificial Intelligence, Toronto (pp. 381 - 387). Springer. Retrieved from https://link.springer.com/chapter/10.1007/978-3-319-89656-4_44
Subramanian, S. Ganapathi, & Crowley, M. . (2018). Combining MCTS and A3C for Prediction of Spatially Spreading Processes in Forest Wildfire Setting. In 31st Canadian Conference on Artificial Intelligence, Toronto (pp. 285-291). Springer. Retrieved from https://link.springer.com/chapter/10.1007/978-3-319-89656-4_28
Subramanian, S. Ganapathi, & Crowley, M. . (2018). Using Spatial Reinforcement Learning to Build Forest Wildfire Dynamics Models from Satellite Images. Journal of Frontiers in ICT- Environmental Informatics. Retrieved from https://www.frontiersin.org/articles/10.3389/fict.2018.00006/full?&utm_source=Email_to_authors_&utm_medium=Email&utm_content=T1_11.5e1_author&utm_campaign=Email_publication&field=&journalName=Frontiers_in_ICT&id=334036
2019
Bhalla, S. , Subramanian, S. Ganapathi, & Crowley, M. . (2019). Learning Multi-Agent Communication with Reinforcement Learning. In Conference on Reinforcement Learning and Decision Making. Retrieved from http://rldm.org/papers/abstracts.pdf
Subramanian, S. Ganapathi, Poupart, P. , Taylor, M. , & Hegde, N. . (2019). Multi Type Mean Field Reinforcement Learning. In Conference on Reinforcement Learning and Decision Making. Retrieved from http://rldm.org/papers/abstracts.pdf
Bhalla, S. , Subramanian, S. Ganapathi, & Crowley, M. . (2019). Training Cooperative Agents for Multi-Agent Reinforcement Learning. In International Conference on Autonomous Agents and Multiagent System (AAMAS 2019), Montreal, Canada. Retrieved from http://www.ifaamas.org/Proceedings/aamas2019/pdfs/p1826.pdf
2020
Gottipati, S. Krishna, Pathak, Y. , Nuttall, R. , Sahir, , Chunduru, R. , Touati, A. , Subramanian, S. Ganapathi, et al. (2020). Maximum Reward Formulation In Reinforcement Learning. In Deep Reinforcement Learning Workshop. NeurIPS 2020. Retrieved from https://arxiv.org/pdf/2010.03744.pdf
Bhalla, S. , Subramanian, S. Ganapathi, & Crowley, M. . (2020). Deep Multi Agent Reinforcement Learning for Autonomous Driving. In Canadian AI . Springer LNCS. Retrieved from https://link.springer.com/chapter/10.1007/978-3-030-47358-7_7
Jain, P. , Coogan, S. C. P. , Subramanian, S. Ganapathi, Crowley, M. , Taylor, S. , & Flannigan, M. D. . (2020). A review of machine learning applications in wildfire science and management. Environmental Reviews. Retrieved from https://arxiv.org/pdf/2003.00646.pdf
Subramanian, S. Ganapathi, Poupart, P. , Taylor, M. E. , & Hegde, N. . (2020). Multi Type Mean Field Reinforcement Learning. In International Conference on Autonomous Agents and Multi agent Systems (AAMAS 2020), Aukland, New Zealand. IFAAMAS. Retrieved from https://arxiv.org/pdf/2002.02513.pdf
2021
Lee, K. Ming, Subramanian, S. Ganapathi, & Crowley, M. . (2021). Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments. In Neural Information Processing Systems (NeurIPS) - Deep Reinforcement Learning workshop. Retrieved from https://arxiv.org/pdf/2111.01100.pdf
Tkachuk, V. , Subramanian, S. Ganapathi, & Taylor, M. E. . (2021). The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning. In International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2021), London, UK - Adaptive Learning Agents Workshop. Retrieved from https://arxiv.org/pdf/2103.04416.pdf
Subramanian, S. Ganapathi, Taylor, M. E. , Crowley, M. , & Poupart, P. . (2021). Partially Observable Mean Field Reinforcement Learning. In International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2021), London, UK. Retrieved from https://arxiv.org/pdf/2012.15791.pdf
2022
Subramanian, S. Ganapathi, Taylor, M. E. , Crowley, M. , & Poupart, P. . (2022). Decentralized Mean Field Games. In AAAI Conference on Artificial Intelligence (2022), Vancouver, BC, Canada. AAAI press. Retrieved from https://arxiv.org/pdf/2112.09099.pdf
Subramanian, S. Ganapathi, Taylor, M. E. , Larson, K. , & Crowley, M. . (2022). Multi-Agent Advisor Q-Learning. Journal of Aritificial Intelligence Research (JAIR), 74, 1--74. Retrieved from https://jair.org/index.php/jair/article/view/13445/26794