ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design

no code implementations • 15 Jun 2023 • Srivatsan Krishnan, Amir Yazdanbaksh, Shvetank Prakash, Jason Jabbour, Ikechukwu Uchendu, Susobhan Ghosh, Behzad Boroujerdian, Daniel Richins, Devashree Tripathy, Aleksandra Faust, Vijay Janapa Reddi

The ease of data collection and aggregation in ArchGym facilitates research in ML-aided architecture design space exploration.

Jump-Start Reinforcement Learning

no code implementations • 5 Apr 2022 • Ikechukwu Uchendu, Ted Xiao, Yao Lu, Banghua Zhu, Mengyuan Yan, Joséphine Simon, Matthew Bennice, Chuyuan Fu, Cong Ma, Jiantao Jiao, Sergey Levine, Karol Hausman

In addition, we provide an upper bound on the sample complexity of JSRL and show that with the help of a guide-policy, one can improve the sample complexity for non-optimism exploration methods from exponential in horizon to polynomial.

reinforcement-learning Reinforcement Learning (RL)

Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation

no code implementations • 18 Feb 2018 • Fengyi Tang, Kaixiang Lin, Ikechukwu Uchendu, Hiroko H. Dodge, Jiayu Zhou

Even though there is mild cognitive decline in MCI patients, they have normal overall cognition and thus is challenging to distinguish from normal aging.

reinforcement-learning Reinforcement Learning (RL)