ppo-trader
Unverified ML strategy on Indices by VincentLongpre. BotFinder score 18 out of 100.
Developing, training, and assessing the performance of a Proximal Policy Optimization (PPO) Stock Trading Agent.
Source: github
BotFinder analysis pending.
ppo-trader
Reimplementing PPO and Assessing its Performance in Stock Trading Strategies By Alexandre Diz Ganito, Vincent Longpré and Igman Talbi. Final project, COMP579 : Reinforcement Learning - Winter 2024, Prof. Doina Precup. McGill University Table of Contents - Introduction - Models - Installation - Usage - Contributing - License Introduction This project aims to reimplement the Proximal Policy Optimization (PPO) algorithm from scratch using PyTorch. Our goal is to achieve comparable results to Stable Baselines' implementation across multiple environments. We conduct comparisons between our PPO implementation and Stable Baselines' version on the Pendulum environment and a custom StockEnv environment containing the 30 constituent stocks of the Dow Jones index. Models In our project, we developed two distinct classes to facilitate experimentation and comparison: 1. PPO: This class represents our final implementation of the Proximal Policy Optimization (PPO) algorithm. It incorporates strategies and configurations that were identified through iterative testing as contributing to improved perf
⚠ 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)