DeepRL-trade
Unverified ML strategy on Multi by ebrahimpichka. BotFinder score 18 out of 100.
Algorithmic Trading Using Deep Reinforcement Learning algorithms (PPO and DQN)
Source: github
BotFinder analysis pending.
DeepRL-trade
DeepRL-trade Algorithmic Trading Using Deep Reinforcement Learning (PPO & DQN) --- Introduction In quantitative finance, stock trading is essentially a dynamic decision problem — deciding where, at what price, and how much to trade in a stochastic, dynamic, and complex market. Deep reinforcement learning (DRL) enables modelling and solving these sequential decision problems with a human-like approach. This project trains two DRL agents — Proximal Policy Optimization (PPO) and Deep Q-Learning (DQN) — to autonomously make trading decisions on GOOG stock and compares their performance against a Buy & Hold benchmark using risk-adjusted metrics. --- Project Structure --- Quick Start 1. Install 2. Configure API keys (optional) 3. Train 4. Evaluate 5. Visualise --- Configuration All settings are in YAML files under configs/. The system works in layers: 1. configs/default.yaml — all defaults 2. Experiment YAML (e.g. ppogoog.yaml) — overrides specific keys 3. CLI --override — overrides anything at runtime Key sections: data, env, agent (with ppo/dqn sub-sections), evaluation, tracking, paths.
⚠ 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)