eb49e2a0f7
C51 distributional Q-network with GPU Thompson selection borrowed
minimally from production (alpha_c51.cu: forward, project, grad,
expected_q, thompson_select kernels; ~260 lines). Uses Huber
negative-tail compression in projection per production
block_bellman_project_f. Action selection 100% GPU via mapped-pinned
i32 output + __threadfence_system + host volatile read (matches
gpu_training_guard MappedBuffer pattern).
Backtest result (2D sweep, 500 episodes per cell, 30 cells):
cost=0 C51 +10.41 vs linear-Q -15.72 (+26pt, BEATS Phase 1d.4
no-RL baseline +4.4 by 6pt)
cost=0.125 C51 -13.81 vs -29.17 (+15pt closes half-tick gap)
Win rate at cost=0 best τ: linear-Q 0.008 → C51 0.552.
Calibration hypothesis vindicated; documented in
memory/pearl_c51_thompson_closed_phase_e3_gap.md.
Also in this commit (Phase E.3 follow-up cleanup):
- --pruned-actions falsified (2.4× worse Sharpe). Documented in
memory/pearl_action_pruning_falsified.md.
- --real-spread falsified for ES futures (76% of bars at 1-tick floor).
- SnapshotRow bid_l/ask_l extended from [f32; 3] to [f32; 10].
L4-L10 synthesized in this commit; real MBP-10 peek lands in E.4.A T5.
- docs/isv-slots.md updated per kernel-audit-doc hook requirement.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
176 lines
4.6 KiB
JSON
176 lines
4.6 KiB
JSON
{
|
|
"action_entropy_ema": 0.6501350402832031,
|
|
"all_pass": false,
|
|
"alpha_m": 0.8999999761581421,
|
|
"c51": true,
|
|
"c51_n_atoms": 51,
|
|
"c51_vmax": 10.0,
|
|
"c51_vmin": -10.0,
|
|
"early_q_movement_ema": 0.012797871604561806,
|
|
"eps_end": 0.05000000074505806,
|
|
"eps_start": 0.5,
|
|
"final_stacker_kelly_attenuation": 0.10000000149011612,
|
|
"final_stacker_threshold": 0.3718600869178772,
|
|
"final_trade_rate_observed_ema": 0.14652971923351288,
|
|
"gamma": 0.9900000095367432,
|
|
"grad_clip": 1.0,
|
|
"horizon": 600,
|
|
"kc_log": [
|
|
{
|
|
"early_mvmt": 0.0019911762792617083,
|
|
"entropy": 1.5733345746994019,
|
|
"episode": 50,
|
|
"q_spread": 31.75593376159668,
|
|
"rvr": 1.044257402420044
|
|
},
|
|
{
|
|
"early_mvmt": 0.0024081910960376263,
|
|
"entropy": 1.4243084192276,
|
|
"episode": 100,
|
|
"q_spread": 23.955223083496094,
|
|
"rvr": 1.0445903539657593
|
|
},
|
|
{
|
|
"early_mvmt": 0.0031225469429045916,
|
|
"entropy": 1.310657262802124,
|
|
"episode": 150,
|
|
"q_spread": 19.488779067993164,
|
|
"rvr": 1.0448148250579834
|
|
},
|
|
{
|
|
"early_mvmt": 0.0038882701192051172,
|
|
"entropy": 1.2122981548309326,
|
|
"episode": 200,
|
|
"q_spread": 17.970020294189453,
|
|
"rvr": 1.0449012517929077
|
|
},
|
|
{
|
|
"early_mvmt": 0.004593650344759226,
|
|
"entropy": 1.132895827293396,
|
|
"episode": 250,
|
|
"q_spread": 60.273643493652344,
|
|
"rvr": 1.0449382066726685
|
|
},
|
|
{
|
|
"early_mvmt": 0.005275565665215254,
|
|
"entropy": 1.06606125831604,
|
|
"episode": 300,
|
|
"q_spread": 44.775360107421875,
|
|
"rvr": 1.0449564456939697
|
|
},
|
|
{
|
|
"early_mvmt": 0.005944964475929737,
|
|
"entropy": 1.0079469680786133,
|
|
"episode": 350,
|
|
"q_spread": 35.19337463378906,
|
|
"rvr": 1.0449739694595337
|
|
},
|
|
{
|
|
"early_mvmt": 0.0066252113319933414,
|
|
"entropy": 0.9588310718536377,
|
|
"episode": 400,
|
|
"q_spread": 23.109146118164062,
|
|
"rvr": 1.0449974536895752
|
|
},
|
|
{
|
|
"early_mvmt": 0.007311227265745401,
|
|
"entropy": 0.9154046773910522,
|
|
"episode": 450,
|
|
"q_spread": 30.995208740234375,
|
|
"rvr": 1.0450423955917358
|
|
},
|
|
{
|
|
"early_mvmt": 0.007989339530467987,
|
|
"entropy": 0.8766676187515259,
|
|
"episode": 500,
|
|
"q_spread": 28.47087287902832,
|
|
"rvr": 1.0450869798660278
|
|
},
|
|
{
|
|
"early_mvmt": 0.008644208312034607,
|
|
"entropy": 0.8420573472976685,
|
|
"episode": 550,
|
|
"q_spread": 20.39789390563965,
|
|
"rvr": 1.0451369285583496
|
|
},
|
|
{
|
|
"early_mvmt": 0.009266316890716553,
|
|
"entropy": 0.8106650114059448,
|
|
"episode": 600,
|
|
"q_spread": 15.783662796020508,
|
|
"rvr": 1.0452359914779663
|
|
},
|
|
{
|
|
"early_mvmt": 0.009855338372290134,
|
|
"entropy": 0.7826521992683411,
|
|
"episode": 650,
|
|
"q_spread": 15.634352684020996,
|
|
"rvr": 1.0453643798828125
|
|
},
|
|
{
|
|
"early_mvmt": 0.010388685390353203,
|
|
"entropy": 0.7577194571495056,
|
|
"episode": 700,
|
|
"q_spread": 13.28182315826416,
|
|
"rvr": 1.0455031394958496
|
|
},
|
|
{
|
|
"early_mvmt": 0.010871796868741512,
|
|
"entropy": 0.7353291511535645,
|
|
"episode": 750,
|
|
"q_spread": 13.777722358703613,
|
|
"rvr": 1.0455645322799683
|
|
},
|
|
{
|
|
"early_mvmt": 0.011310325935482979,
|
|
"entropy": 0.714767575263977,
|
|
"episode": 800,
|
|
"q_spread": 49.52091979980469,
|
|
"rvr": 1.0456281900405884
|
|
},
|
|
{
|
|
"early_mvmt": 0.011722153052687645,
|
|
"entropy": 0.696082353591919,
|
|
"episode": 850,
|
|
"q_spread": 25.91876983642578,
|
|
"rvr": 1.0456620454788208
|
|
},
|
|
{
|
|
"early_mvmt": 0.01210756879299879,
|
|
"entropy": 0.6795051693916321,
|
|
"episode": 900,
|
|
"q_spread": 19.0417423248291,
|
|
"rvr": 1.045680284500122
|
|
},
|
|
{
|
|
"early_mvmt": 0.012464887462556362,
|
|
"entropy": 0.6642012000083923,
|
|
"episode": 950,
|
|
"q_spread": 31.48348045349121,
|
|
"rvr": 1.0456589460372925
|
|
},
|
|
{
|
|
"early_mvmt": 0.012797871604561806,
|
|
"entropy": 0.6501350402832031,
|
|
"episode": 1000,
|
|
"q_spread": 26.82328224182129,
|
|
"rvr": 1.0456655025482178
|
|
}
|
|
],
|
|
"lr": 0.00009999999747378752,
|
|
"n_allowed_actions": 9,
|
|
"n_episodes": 1000,
|
|
"pass_early": true,
|
|
"pass_entropy": false,
|
|
"pass_q_spread": true,
|
|
"pass_rvr": true,
|
|
"phase": "E.1 Task 12",
|
|
"pruned_actions": false,
|
|
"q_init_norm": 17.471145629882812,
|
|
"q_spread_ema": 26.82328224182129,
|
|
"return_vs_random_ema": 1.0456655025482178,
|
|
"reward_scale": 1000.0,
|
|
"target_update_every": 10,
|
|
"tau": 0.029999999329447746,
|
|
"trade_rate_target": 0.07999999821186066
|
|
} |