General parameter-shift rules for quantum gradients

Asymptotic Estimation of Shift Parameter of a Quantum State∗

The rise of quantum estimation theory dates back to the late 1960s – 1970s (see [8], [9]). It was initially developed as an adequate mathematical framework for design of optimal receiver in quantum communication channels, and later turned out to be relevant also for clarification of some foundational issues of quantum measurement. New interest to quantum estimation theory was brought by the dev...

Parameter-exploring policy gradients

We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in parameter space, which leads to lower variance gradient estimates than obtained by regular policy gradient methods. We show that for several complex control tasks, including robust standing with a humanoid robot, this method ...

Quantum Theory from Symmetries in a General Statistical Parameter Space

The aim of this paper is to show a connection between an extended theory of statistical experiments on the one hand and the foundation of quantum theory on the other hand. The main aspects of this extension are: One assumes a hyperparameter space Φ common to several potential experiments, and a basic symmetry group G associated with this space. The parameter θa of a single experiment, looked up...

Quantum parameter estimation using general single-mode Gaussian states

Policy Gradients with Parameter-Based Exploration for Control

We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in parameter space, which leads to lower variance gradient estimates than those obtained by policy gradient methods such as REINFORCE. For several complex control tasks, including robust standing with a humanoid robot, we show t...