448b61d095
The 4-branch DQN (direction x magnitude) had 3 degenerate variants (Short25, Flat, Long25) that all mapped to 0.0 target exposure when direction=Flat, causing 82% Flat collapse. Collapse these into a single Flat variant, giving 7 levels (ShortSmall/Half/Full, Flat, LongSmall/Half/Full) and 63 total factored actions (7x3x3). - ExposureLevel enum: 9 variants -> 7 (add direction/magnitude/from_dir_mag) - FactoredAction: 81 -> 63 total actions, from_index/to_index updated - DQN epsilon-greedy: use from_dir_mag() instead of dir*3+mag indexing - DQN config: num_actions default 9 -> 7 - PPO action space: 45 -> 63 actions, action masking updated - Signal adapter CUDA kernel: 5-bin -> 7-bin exposure aggregation - All tests updated for new variant names and index ranges Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
backtesting
Strategy backtesting engine for simulating trading strategies against historical market data.
Key Types
Backtester— main backtesting engineBacktestConfig— simulation configuration (time range, instruments, slippage, commissions)BacktestResults— performance metrics (Sharpe, max drawdown, alpha, beta, Sortino)
Features
- Historical data replay from Parquet files (ticks, order book snapshots, candles)
- Configurable slippage models (fixed, percentage, volume-based)
- Commission modeling (fixed, percentage, per-contract)
- Pluggable strategy interface
Usage
use backtesting::{Backtester, BacktestConfig};
let config = BacktestConfig { /* ... */ };
let results = backtester.run(&strategy)?;