Hybrid reinforcement learning with expert state sequences
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
We introduce the notion of fault tolerant mechanism design, which extends the standard game theoretic framework of mechanism design to allow for uncertainty about execution. Specifically, we define the problem of task allocation in which the private information of the agents is not only their costs of attempting the tasks but also their probabilities of failure. For several different instances of this setting we present both, positive results in the form of mechanisms that are incentive compatible, individually rational, and efficient, and negative results in the form of impossibility theorems. © 2008 Elsevier B.V. All rights reserved.
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
Jehanzeb Mirza, Leonid Karlinsky, et al.
NeurIPS 2023
Guo-Jun Qi, Charu Aggarwal, et al.
IEEE TPAMI
Tim Erdmann, Stefan Zecevic, et al.
ACS Spring 2024