Donald - AI Futures 5M 15M Timeframe is an overlay trading strategy designed for intraday futures trading. It utilizes rational quadratic kernel regression to construct dynamic momentum zones and smoothed price boundaries on the main price chart. The strategy
Strategy · Pine Script v6 · On the chart
TnSovereign NeuraRL
An experimental strategy that applies a small reinforcement learning agent, a dueling deep Q-network built with the NeuraLib library, to chart data.
GitHub stars1on the repository
Pine versionv6current
Lines of code437
Settings12inputs
LicenceNone stated
Last update2 months ago15 Aug 2026
Add It to Your TradingView Chart
- 1Copy the scriptPress Copy script above. It reads the file straight from GitHub.
- 2Open the Pine EditorOpen a TradingView chart and choose Pine Editor at the bottom of the screen.
- 3Paste over the templateCreate a new strategy, select all of the template text and paste. Press Save and give it a name.
- 4Add it to the chartPress Add to chart. The trades and results appear in the Strategy Tester tab; adjust the settings with the gear icon.
Source Code
The code stays on GitHub. The author has not published this script under an open licence, so ForexR does not show its code. Copy script reads the file straight from GitHub into your clipboard, so you can still try it on your own chart. Ask the author before reusing the code anywhere else.
Overview
An eight-value state vector from price z-score, RSI, ATR ratio, EMA slope, volume, MACD and candle features feeds the network, which learns online from a replay buffer with decaying exploration. Orders use an ATR-based stop loss and a risk-to-reward target with percentage risk sizing. It draws on the price chart and depends on an external library.
- Dueling Q-network trained online
- Replay buffer and epsilon decay settings
- Eight-feature market state vector
- ATR stop loss with reward-to-risk target
- Percent risk position sizing
Details
Published by
raybird on GitHub
Type
Strategy, Pine Script v6
Draws
On the price chart
Category
AI / machine learning
Markets
Any symbol
Timeframes
Any timeframe
Risk Notes
No repainting, lookahead or stacked entries were found in its code or README. That says nothing about how well it works: test it first.
Settings
The inputs you can change from the gear icon on the chart. Defaults are the author's.
| Setting | Type | Default | Variable |
|---|---|---|---|
| State Dimension | int | 8 | state_dim |
| Replay Buffer Size | int | 200 | buffer_size |
| Batch Size | int | 32 | batch_size |
| Discount Factor γ | float | 0.95 | gamma |
| Soft-Update τ | float | 0.01 | tau |
| Initial ε | float | 0.5 | epsilon_init |
| Min ε | float | 0.05 | epsilon_min |
| ε Decay Bars | int | 500 | decay_bars |
| Learning Rate α | float | 0.001 | learning_rate |
| Stop Loss ATR Multiple | float | 2.0 | sl_atr_mult |
| Take Profit R:R Ratio | float | 2.5 | tp_rr_ratio |
| Risk per Trade % | float | 1.0 | risk_per_trade |
Third-party code. ForexR did not write, test or endorse this script, and the summary above was generated automatically from its code and README. Indicators describe the past, and a strategy's backtest can look better than live trading, especially when a script repaints. Check it in the Strategy Tester and on a demo account before you rely on it.
Similar Pine Scripts
This strategy implements a single-layer perceptron machine learning model built from scratch to generate trading signals directly on the price chart. It calculates predictions based on sample size, threshold settings, and optional volatility or volume filters.
This overlay strategy combines a machine-learning distance model with a MACD oscillator to open trades on the price chart. It compares recent history using cosine similarity or Euclidean and Lorentzian distance, then filters direction with selectable moving-av
Donald - AI Futures is a price-chart strategy that estimates inner and outer high-low zones and a smoothed close with rational quadratic kernel regression. It builds bullish and bearish momentum signals, optionally compares volume with a volume-weighted moving
Calculates MACD line and signal line differences, passing current and previous deltas through a two-layer neural network model with ReLU activation functions. User-configurable weights, biases, and threshold values determine output classification signals. The
Knn Filter A007 is a strategy that applies a K-Nearest Neighbors classification algorithm to evaluate historical feature performance and filter out low-probability trade setups. It executes long and short entries based on learned historical patterns. Risk mana
Trade Your Charts With a Regulated Broker
Compare brokers that connect to TradingView, with spreads, minimum deposits and leverage side by side.
Compare brokers