Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2
Published in NeurIPS Workshop on ML in Systems, 2018
We provide a model and framework for predicting cache miss rates using feed forward neural networks
Recommended citation: Rishikesh Jha, Saket Tiwari, Arjun Kuravally, Eliot Moss. (2018). "Cache Miss Rate Predictability via Neural Networks." NeurIPS 2018 Workshop on ML in Systems https://openreview.net/pdf?id=QYQH9w9Z8bO
Published in AAAI, 2019
We derive a practical natural gradient method for the option critic framework in Hierarchical Reinforcement Learning
Recommended citation: Saket Tiwari, & Philip Thomas. (2019). "Natural Option Critic." AAAI 2019 https://arxiv.org/pdf/1812.01488.pdf
Published in NeurIPS, 2022
We provide a new theory for understanding the capacity of neural networks in light of the manifold hypothesis
Recommended citation: Saket Tiwari, & George Konidaris. "Effects of Data Geometry in Early Deep Learning." NeurIPS 2022 https://arxiv.org/abs/2301.00008
Published in Neural Networks Journal, 2023
Provided various benchmarking results and methodologies for lifelong reinforcement learning
Recommended citation: Megan M. Baker, Alexander New, Mario Aguilar-Simon, Ziad Al-Halah, Sébastien M. R. Arnold, Ese Ben-Iwhiwhu, Andrew P. Brna, Ethan Brooks, Ryan C. Brown, Zachary Daniels, Anurag Daram, Fabien Delattre, Ryan Dellana, Eric Eaton, Haotian Fu, Kristen Grauman, Jesse Hostetler, Shariq Iqbal, Cassandra Kent, Nicholas Ketz, Soheil Kolouri, George Konidaris, Dhireesha Kudithipudi, Erik Learned-Miller, Seungwon Lee, Michael L. Littman, Sandeep Madireddy, Jorge A. Mendez, Eric Q. Nguyen, Christine D. Piatko, Praveen K. Pilly, Aswin Raghavan, Abrar Rahman, Santhosh Kumar Ramakrishnan, Neale Ratzlaff, Andrea Soltoggio, Peter Stone, Indranil Sur, Zhipeng Tang, Saket Tiwari, Kyle Vedder, Felix Wang, Zifan Xu, Angel Yanguas-Gil, Harel Yedidsion, Shangqun Yu, Gautam K. Vallabha. (2023). "A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems" Neural Networks Volume 160, 2023. https://www.sciencedirect.com/science/article/abs/pii/S0893608023000072
Published in ICML, 2023
A novel method for learning parameterized skills in reinforcement learning for robotic control using deep neural network
Recommended citation: Haotian Fu, Shangqun Yu, Saket Tiwari, Michael Littman, George Konidaris. (2023). "Meta-Learning Parameterized Skills." ICML 2023 https://proceedings.mlr.press/v202/fu23f.html
Published in ICLR [ORAL: top 1.8% of submitted], 2025
We prove that the state space is a low dimensional manifold for reinforcement learning in the infinite width limit of two layer neural networks and utilise this to improve performance in dog and humanoid environments.
Recommended citation: Saket Tiwari, Omer Gottesman, & George Konidaris. (2025). "Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces." ICLR 2025 https://openreview.net/pdf?id=AP0ndQloqR
Graduate level course, Brown University, Computer Science, 2024
I designed course material and assignments for the sequential decision making course at Brown. This is the course on Reinforcement Learning at Brown. The course was taught by Ron Parr and I was one of two grad TAs in a class of 70 people. The course was well recieved and I personally recieved positive reviewes for my teaching.