TDQN-in-keras
Unverified ML strategy on Multi by DemaciaLarz. BotFinder score 18 out of 100.
Applying the Trading Deep Q-Network algorithm (TDQN) on shares in the hydrogen sector.
Source: github
BotFinder analysis pending.
TDQN-in-keras
Implementing TDQN in Keras Consider as the basic building block of this project the Trading Deep Q-Network algorithm (TDQN) as it is put forward in the paper named: An Application of Deep Reinforcement Learning to Algorithmic Trading which you can find here. Table of Contents 1. Objectives 2. Underlying Assets - Data 3. User-Values / Downstream Application 4. Content 5. Results 6. TDQN Implementation Notes 1 Objectives The objective was to implement the TDQN algorithm on a set of shares from the upcoming hydrogen sector in order to obtain valuable insights into market movements. As it turned out it got applied to historical gold prices for the initial training, and then quite successfully to one hydrogen stock, Powercell Sweden. Here are some nice results: 2 Underlying Assets - Data Powercell Sweden is a fuel cell manufacturer listed on the First North GM Sweden market, here is information on the share and the historical prices, and here is info on the company. You can find analysis and preprocessing as it relates to this project of the actual data here. When it comes to gold, here a
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)