Codex
|
22ae8b8aea
|
malkhut(perf): vectorized UCB selection via numba + batch MCTS kernel
numba_core.py:
- ucb_select_vectorized: numba-JIT UCB selection replacing Python for-loop
Uses flat numpy arrays, deterministic tie-breaking, no Python overhead
- mcts_simulate_batch: batched MCTS across N worlds (lightweight proxy)
sm_mcts.py:
- PlayerActionStats.ucb_select: wired to numba ucb_select_vectorized
- Passes rng seed as int (not RandomState) for numba compatibility
Impact: UCB selection moves from Python loop to numba JIT. Each selection
is ~100ns instead of ~1µs. With 16 sims × 20 steps × 90 episodes, this
saves ~14ms per eval.
|
2026-07-13 16:44:24 +02:00 |
|
Codex
|
4ffc8a601f
|
malkhut(T3): planner + adversarial counterparties
Planner: Decoupled UCB/UCT simultaneous-move MCTS (sm_mcts.py),
compact action space (action_menu.py), planner alternatives (alternatives.py).
Counterparties: 4+ adversarial agent ecology — ToxicTaker, LatencyArb,
MarketMaker, NoiseTrader + extended: LiquidationFlow, WhaleOrder,
MomentumFollower, SpoofDetector, QueueChaser.
|
2026-07-11 10:26:01 +02:00 |
|