{"sources":[{"url":"https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/README.md","quote":"`latt.py` is the same policy with the Gaussian belief replaced by probability mass on 121 cells of 2.5 bps: each step convolves with the price-move kernel, a step with no own trade zeroes the cells where the arb would have traded, and the first trade of a step becomes a mixture of a point mass at th"},{"url":"https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/latt.py","quote":"HC = 2.5e-4            # cell width (log)\nNC = 121               # cells: +-150 bps\nN0 = NC // 2\nSIG = 0.000945\n\n\ndef kernel(sig, hc):\n    s = sig / hc; M = int(math.ceil(4.0 * s))\n    w = [math.exp(-0.5 * (k / s) ** 2) for k in range(-M, M + 1)]\n    t = sum(w)\n    return [v / t for v in w], M\n\nKER,"},{"url":"https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/run.py","quote":"A blind policy never receives the true price, the rival's spot, the arb flag, the order count or the run's\nparameters. If it keeps `m` (ln of its price estimate) the price error is reported; if it sets `first` and\n`is_arb` on each call, so is the share of first trades it misread.\n\"\"\"\nimport sys, os,"},{"url":"https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/ref/lattice_qm.json","quote":"{\"policy\": \"lattice\", \"opt\": {\"qm\": \"qm_k1e-5.json\"}, \"rows\": [{\"seed\": 10000, \"edge\": 443.66351980397485, \"retail\": 464.0539647644912, \"arb\": -20.3904449605146, \"rv\": 63930.34408248028, \"av\": 20954.94821548155, \"first\": 6266, \"misread\": 1106, \"se\": "},{"url":"https://api.imdnotdead.fun/artifacts/1134b0f83ff44cf484f8dc780a5c7f0e5d08d2cbbfad3d4ee2d3578ae6fa1ac6","quote":"{\"key\":\"numba-3\",\"gates_match\":true,\"gates\":{\"10000\":443.66352,\"10001\":571.977293,\"10002\":526.411631},\"holdout_identity\":{\"n\":64,\"differ\":0,\"max_abs_diff\":2.739284354902338e-10},\"seconds_per_run\":{\"pure\":0.478,\"numba\":0.00858},\"speedup\":55.7,\"code_zb"}]}