futures-trading-gym
Unverified ML strategy on Multi by onesamblack. BotFinder score 18 out of 100.
An OpenAI gym environment for futures trading
Source: github
BotFinder analysis pending.
futures-trading-gym
futures-trading-gym An OpenAI gym environment for futures trading The futures market is different than a typical stock trading environment, in that contracts move in fixed increments, and each increment (tick) is worth a variable amount depending on the contract traded. This environment is designed for a single contract - for a single security type. Accompanying this environment is the concept of a TimeSeriesState, which is a variable (n x m) window of all the features representing the state, where n represent the number of steps in the window and m represents the number of features. This allows you to define the state that your agent uses to determine the action. Some possibillities are: - An embedding - A window of the last 20 observed values - A scalogram from a wavelet transform - A stack of scalograms - Etc. See envs.utils.TimeSeriesState for more details Action Space This environment accepts 3 different actions at any time state: - 0 - a buy - 1 - a hold (no action) - 2 - a sell The environment does not allow for more than one contract to be traded at a time. If a buy action is
⚠ 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)