most citedA relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

eess.SY2021★ 2 cited

A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems

Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan +2

We revisit the Thompson sampling algorithm to control an unknown linear quadratic (LQ) system recently proposed by Ouyang et al (arXiv:1709.04047). The regret bound of the algorith…