all AI news
Convergence of policy gradient for entropy regularized MDPs with neural network approximation in the mean-field regime. (arXiv:2201.07296v1 [math.OC])
Jan. 20, 2022, 2:10 a.m. | Bekzhan Kerimkulov, James-Michael Leahy, David Šiška, Lukasz Szpruch
cs.LG updates on arXiv.org arxiv.org
We study the global convergence of policy gradient for infinite-horizon,
continuous state and action space, entropy-regularized Markov decision
processes (MDPs). We consider a softmax policy with (one-hidden layer) neural
network approximation in a mean-field regime. Additional entropic
regularization in the associated mean-field probability measure is added, and
the corresponding gradient flow is studied in the 2-Wasserstein metric. We show
that the objective function is increasing along the gradient flow. Further, we
prove that if the regularization in terms of the …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Principal Engineer, Deep Learning
@ Outrider | Remote
Data Analyst (Bangkok based, relocation provided)
@ Agoda | Bangkok (Central World Office)
Data Scientist II
@ MoEngage | Bengaluru
Machine Learning Engineer
@ Sika AG | Welwyn Garden City, United Kingdom