Conference paper
Hybrid reinforcement learning with expert state sequences
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
For any fixed dimension d, thelinear programming problem with ninequality constraints can be solved on a probabilistic CRCW PRAM withO1994processors almost surely in constant time. The algorithm always findsthe correct solution. Withnd/log2dprocessors, the probability that the algorithm will not finish withinO(d2log2dtime tends to zero exponentially withn. © 1994, ACM. All rights reserved.
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
Chen-chia Chang, Wan-hsuan Lin, et al.
ICML 2025
Yi Zhou, Parikshit Ram, et al.
ICLR 2023
Hannah Kim, Celia Cintas, et al.
IJCAI 2023