#q-learning

again, transfem abusers exist, we know this. why is there a focus on transfems in particular, knowing that anyone can abuse a transmasc? i’m just wanting to be accurate here

i appreciate that you are actually asking a question instead of just telling me to die, so i will try to explain this as best as i can. i am tiredbut i want to be honest with you.

the reason this project focuses on transfem abusers isn’t because i think they are the only people who abuse transmascs; it’s because it is a uniquely difficult, taboo, and "touchy" subject. abuse doesn't exist in a vacuum, and when it involves someone from a vulnerable group,especially a group that is also suffering under systemic oppression, the conversation becomes almost impossible to have without people being silenced or labeled a bigot. i wanted to create a space where that specific kind of pain could be acknowledged, because there was nowhere else for it to go.

i have thought about opening this up to include cases where the abuser is also transmasculine, because i know that happens too, and survivors deserve support regardless of the abuser's demographic. honestly, i was just worried that if i did that right away, it would become an overwhelming or disproportionate part of the discourse, and the primary focus (which is the specific, often ignored reality of abuse by transfems) would get lost.

What is Reinforcement Learning? – A Quick Overview Reinforcement learning (RL) represents a fascinating branch of artificial intelligence where an agent learns to make decisions within an environment to maximize a cumulative reward. Unlike supervised learning, which relies on labeled data, reinforcement learning agents learn through trial and error, receiving feedback in the form of rewards or…

Q-Learnıng Based Real Tıme Path Plannıng for Mobıle Robots

by Halil Cetin | Akif Durdu | M. Fatih Aslan | M. Mustafa Kelek "Q-Learnıng Based Real Tıme Path Plannıng for Mobıle Robots" 

Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-1 , December 2019, 

URL: https://www.ijtsrd.com/papers/ijtsrd29625.pdf  

Paper URL: https://www.ijtsrd.com/engineering/computer-engineering/29625/q-learn%C4%B1ng-based-real-t%C4%B1me-path-plann%C4%B1ng-for-mob%C4%B1le-robots/halil-cetin

pharmacy journal, open access journal of engineering, research publication

Paper with Code series: Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation

  The two fields of Machine Learning and Quantum Computing are the most important ones for today’s computer science in general. A new field of study is actually emerging with the appropriate name of Quantum Machine Learning. The important sub-field of Reinforcement Learning is also being used by researchers in Quantum Computing and today’s paper choice by the Paper with Code series is all about…

This weekend was Santa Con 2017. Woo! It was also DLSG XV (deep learning study group 15) put together by Jon Krohn where we learned about reinforcement learning. I'm summarizing it here.

High Level 

Reinforcement learning is an approach to ML type problems that has become popular. Reinforcement learning is often applied to Atari games like pac man or ping-pong. The framework it uses is different than other kinds of deep learning methods. Instead of simply having an input and an output through some neural network architecture you consider the problem from the point of view of the player or Agent. The agent can interact with its world in varying degrees of discrete or continuous decisions. These decisions or Actions lead to new states and cause the agent to succeed or fail at its objective. This success is a measurable reward which is also used to then update the policies that the agent uses to make future decisions. Actions can be as simple as moving up down left or right and states are like the position of the agent and reward is the score of the game or whether or not the agent dies / loses. 

Deeper

Reinforcement learning can happen in different ways and there are several algorithms that do this. A Q-function is used to describe what the agent should do. It is the function that keeps all the policies the agent will use in the game or environment. A neural network is used to approximate the Q-function. A perfect Q-function indicates that the agent knows how to act optimally. π(s) = maxQ(s,a). Policy (pi) as a function of state equals the max Q function as a function of state and action. Q functions answer how good is a state action pair while a value function answers how good is a state

A = Q - V

自分にはまだ早かった．面白そうだからいつかは読みたいと思う．