<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Python |</title><link>https://aroraanshu26.github.io/tags/python/</link><atom:link href="https://aroraanshu26.github.io/tags/python/index.xml" rel="self" type="application/rss+xml"/><description>Python</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 03 Jun 2024 00:00:00 +0000</lastBuildDate><image><url>https://aroraanshu26.github.io/media/icon_hu_da05098ef60dc2e7.png</url><title>Python</title><link>https://aroraanshu26.github.io/tags/python/</link></image><item><title>Hands-on Reinforcement Learning</title><link>https://aroraanshu26.github.io/projects/scikit/</link><pubDate>Mon, 03 Jun 2024 00:00:00 +0000</pubDate><guid>https://aroraanshu26.github.io/projects/scikit/</guid><description>&lt;p&gt;This is my exploratory project in Reinforcement Learning, where I have implemented common learning algorithms such as Q-learning, to play the mountain car game. I have also implemented different greedy, epsilon greedy, UCB sampling strategy, and have plotted their regret versus number of samples.&lt;/p&gt;</description></item><item><title>Trading Bot</title><link>https://aroraanshu26.github.io/projects/trading-bot/</link><pubDate>Wed, 27 Dec 2023 00:00:00 +0000</pubDate><guid>https://aroraanshu26.github.io/projects/trading-bot/</guid><description>&lt;p&gt;Developed a machine learning pipeline for stock trend prediction using technical analysis indicators on NIFTY50 data. The project involved extracting and preprocessing market data, engineering features using indicators such as MACD, RSI, Bollinger Bands, ADX, and Aroon, handling missing values and normalization, and training models to predict short-term gains and trading positions (buy, sell, or hold).&lt;/p&gt;</description></item></channel></rss>