Zobrazeno 1 - 10
of 478
pro vyhledávání: '"Chatterjee, Samrat"'
Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful convergence to
Externí odkaz:
http://arxiv.org/abs/2402.03590
Autor:
Oster, Matthew R., Amburg, Ilya, Chatterjee, Samrat, Eisenberg, Daniel A., Thomas, Dennis G., Pan, Feng, Ganguly, Auroop R.
Resilient operation of interdependent infrastructures against compound hazard events is essential for maintaining societal well-being. To address consequence assessment challenges in this problem space, we propose a novel tri-level optimization model
Externí odkaz:
http://arxiv.org/abs/2310.10587
Development of autonomous cyber system defense strategies and action recommendations in the real-world is challenging, and includes characterizing system state uncertainties and attack-defense dynamics. We propose a data-driven deep reinforcement lea
Externí odkaz:
http://arxiv.org/abs/2302.01595
Autor:
Rahman, Aowabin, Bhattacharya, Arnab, Ramachandran, Thiagarajan, Mukherjee, Sayak, Sharma, Himanshu, Fujimoto, Ted, Chatterjee, Samrat
Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-oriented coordination and coll
Externí odkaz:
http://arxiv.org/abs/2212.10064
Conformal prediction is a widely used method to quantify the uncertainty of a classifier under the assumption of exchangeability (e.g., IID data). We generalize conformal prediction to the Hidden Markov Model (HMM) framework where the assumption of e
Externí odkaz:
http://arxiv.org/abs/2210.02271
Advances in ad hoc teamwork have the potential to create agents that collaborate robustly in real-world applications. Agents deployed in the real world, however, are vulnerable to adversaries with the intent to subvert them. There has been little res
Externí odkaz:
http://arxiv.org/abs/2208.05071
Publikováno v:
In Mathematical Biosciences June 2024 372
Autor:
Gangwe, Anil1 (AUTHOR), Chatterjee, Samrat2 (AUTHOR), Singh, Abhishek3 (AUTHOR), Agrawal, Deepshikha2 (AUTHOR), Rahangdale, Diksha4 (AUTHOR), Azad, Raj5 (AUTHOR)
Publikováno v:
Indian Journal of Ophthalmology. Feb2024, Vol. 72 Issue 2, p258-263. 6p.
Nonlinear dynamical systems such as Lorenz63 equations are known to be chaotic in nature and sensitive to initial conditions. As a result, a small perturbation in the initial conditions results in deviation in state trajectory after a few time steps.
Externí odkaz:
http://arxiv.org/abs/2106.08489