3

A tabular system for agent decisions is a direct and simple map of percept to control choice. For each percept received, the agent looks up the percept and cross-references it to the action it should take. In order to construct this, you need to list all percepts in full detail, with the associated control choice. Clearly that is not going to be feasible for ...


3

I think you are looking for quantum machine learning (QML), which is a relatively new field that sits at the intersection of quantum computing and machine learning. If you are not familiar with quantum computing (QC) and you are interested in QML, I suggest that you follow this course by prof. Umesh Vazirani and read the book Quantum Computing for Computer ...


3

Is there a term for the humans who do [machine] learning? Typically you will see "AI researchers" for people studying machine intelligence in general, or "data scientists" for people working with statistics or studying specific solutions in machine learning. Both those terms are used quite flexibly, and generally understood to be ...


1

You might be able to glean what you want from Chapter 13 or Sutton & Barto's Reinforcement Learning: An Introduction, which deals with policy gradient algorithms, and includes pseudocode for a variety of agents based on linear approximation using softmax regression. From your description, you appear to be using - or should consider - softmax regression ...


1

Why do you want to think of these algorithms as agents? An agent is an abstract and higher-level concept than the concept of an algorithm, which is just a set of instructions. You could have two agents, one that is supposed to find the minimum spanning tree and another that is supposed to find the shortest path between a source and goal nodes. In both ...


1

It depends on whether the action is part of the input or output of a neural network estimating the Q-value(state, action). The network on the left has the state as input and outputs one scalar value for each of the categorical actions. It has the advantage of being easy to setup and only needs one network evaluation to predict the Q-value for all actions. ...


Only top voted, non community-wiki answers of a minimum length are eligible