#markovian — Public Fediverse posts

'Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence', by Ashwin Pananjady, Vidya Muthukumar, Andrew Thangaraj.

http://jmlr.org/papers/v25/24-0511.html

#markovian #markov #estimation

'Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence', by Ashwin Pananjady, Vidya Muthukumar, Andrew Thangaraj.

http://jmlr.org/papers/v25/24-0511.html

#markovian #markov #estimation

'Convex Reinforcement Learning in Finite Trials', by Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli.

http://jmlr.org/papers/v24/22-1514.html

#reinforcement #optimality #markovian

'Convex Reinforcement Learning in Finite Trials', by Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli.

http://jmlr.org/papers/v24/22-1514.html

#reinforcement #optimality #markovian

On Wednesday Tatiana Vovk explained to me how the character of environment measurements influences the #entanglement of the realized #quantum trajectory.
https://arxiv.org/abs/2111.12048

When you simulate #markovian dynamics of an open system through such trajectories better use #homodyne operators instead of number measurements. Unless, that is, you want to generate volume law entanglement in most of your trajectories 😂 Then do the latter. 😊

Multi-Agent Off-Policy TDC with Near-Optimal Sample and Communication Complexities

Ziyi Chen, Yi Zhou, Rong-Rong Chen

https://openreview.net/forum?id=tnPjQpYk7D

#sampling #markovian #agents

Multi-Agent Off-Policy TDC with Near-Optimal Sample and Communication Complexities

Ziyi Chen, Yi Zhou, Rong-Rong Chen

https://openreview.net/forum?id=tnPjQpYk7D

#sampling #markovian #agents