gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(cuda): force-close existing position on DD trip / cooldown entry

Browse Source 
Cluster v5 alpha-rl-rjsjq step 371 revealed worst-account session_pnl
growing monotonically across cooldown windows (-$3.7k → -$9.3k from
step 100 → 371). Root cause: when DD triggers, actions_to_market_targets
forces {side=2, size=0} — a no-op that suppresses EVERY action type
including trail-stop-driven closes. If the account was holding a
losing position when DD fired, that position bleeds mark-to-market for
the entire 500-step cooldown with no exit path.

Fix: on first DD/cooldown step, emit a closing market order matched to
the current position (side=1 sell for long, side=0 buy for short, size
= |position_lots|). Once flat, subsequent cooldown steps emit the
existing no-op. Net effect: account closes its position at the moment
of DD trip, then sits flat until its recovery clock expires.

Validation: 13/13 risk_stack_invariants pass, 20/20 trade_management
pass, integrated_trainer_smoke passes. Local b=128 1k smoke:
  qpa: +0.95 (best result of session)
  mean_active: +$47k
  worst: stabilizes at -$11.8k (vs unbounded growth pre-fix); residual
  loss is from fat-tail single-step market moves that cross dd_limit
  before the controller can react — out of scope for this fix.
This commit is contained in:
jgrusewski
2026-05-30 23:35:54 +02:00
parent 7064c9269e
commit 1a05af803d
1 changed files with 26 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
crates/ml-alpha/cuda/actions_to_market_targets.cu
View File

@@ -126,15 +126,36 @@ extern "C" __global__ void actions_to_market_targets(
// ────────────────────────────────────────────────────────────────────
// Layer 1 (CMDP hard constraints — spec 2026-05-30-adaptive-risk-management).
// Session-level overrides force Hold regardless of agent's choice.
// Per-batch (one independent backtest session per b); a tripped DD
// or active cooldown on session `b` does NOT lock out the others.
// Session-level overrides force the account FLAT regardless of agent's
// choice. Per-batch (one independent backtest session per b); a tripped
// DD or active cooldown on session `b` does NOT lock out the others.
//
// Fix E (2026-05-30): emit a *closing* market order when the account
// is non-flat — otherwise an existing losing position bleeds m2m for
// the entire 500-step cooldown with no exit (trail stops are also
// suppressed by this branch). Cluster alpha-rl-rjsjq step 371 showed
// worst session_pnl growing monotonically -$3.7k → -$9.3k from
// exactly this mechanism.
//
// Once the position is flat, subsequent cooldown steps emit a true
// no-op (side=2, size=0) and the account waits for its recovery clock.
// ────────────────────────────────────────────────────────────────────
const bool dd_triggered = session_dd_triggered_per_batch[b] >= 0.5f;
const bool in_cooldown = cooldown_remaining_per_batch[b] > 0.0f;
if (dd_triggered || in_cooldown) {
market_targets[b * 2 + 0] = 2; // no-op side
market_targets[b * 2 + 1] = 0; // size = 0
if (position_lots > 0) {
// long → close via sell
market_targets[b * 2 + 0] = 1;
market_targets[b * 2 + 1] = position_lots;
} else if (position_lots < 0) {
// short → close via buy
market_targets[b * 2 + 0] = 0;
market_targets[b * 2 + 1] = -position_lots;
} else {
// already flat → true no-op
market_targets[b * 2 + 0] = 2;
market_targets[b * 2 + 1] = 0;
}
return;
}