{ "config": { "d_hidden": 64, "output_dim": 10, "num_layers": 12, "sigma": 0.03, "batch_size": 256, "num_steps": 5000, "lr_fb": 0.001, "lam": 0.1, "K": 8, "ema_momentum": 0.995, "sigma_bridge": 0.03, "eval_every": 500, "seed": 42, "gpu": 0, "output_dir": "results/toy_lq" }, "log": { "steps": [ 1, 500, 1000, 1500, 2000, 2500, 3000, 3500, 4000, 4500, 5000 ], "state_bridge_loss": [ 66.01814270019531, 2.058396816253662, 2.191567897796631, 2.1112077236175537, 2.2748100757598877, 2.1154427528381348, 2.0553503036499023, 1.966332197189331, 2.1147494316101074, 2.007577896118164, 2.0389387607574463 ], "credit_bridge_loss": [ 112.22884368896484, 0.5559965372085571, 0.36617255210876465, 0.22275042533874512, 0.13448813557624817, 0.0859837457537651, 0.06448937207460403, 0.03930438682436943, 0.033317387104034424, 0.03704077750444412, 0.02309737727046013 ], "dfa_costate_cos": [ 0.0011988391992277824, 0.007705975646296373, -0.0006242827870524847, 0.0037568132393062115, 0.004209253507164808, -0.0012397096635630499, 0.0033803660816584644, 0.003754911944270134, 0.002183924035097544, 0.0057398807973815845, 0.0028941635615550554 ], "state_costate_cos": [ 0.009303608121207127, 0.9451924241506137, 0.9427064611361577, 0.9456643370481638, 0.947175892499777, 0.9486432488148029, 0.9405259856810937, 0.9429925313362708, 0.9463646090947665, 0.9434385620630704, 0.9468063895518963 ], "credit_costate_cos": [ 0.03412332414434506, 0.3051199523302225, 0.2641584941974053, 0.17990898627501267, 0.11904546274588658, 0.03094297769264533, 0.022915477577883463, 0.008693795901938127, 0.0027211602920523058, 0.020937439484091904, 0.033342053540624104 ], "dfa_rho": [ 0.005011526596111556, 0.0020135376447190842, -0.011304221504057447, 0.003935044708972176, 0.0159942601264144, -0.011545649264007807, 0.01096861291443929, 0.0007782066240906715, -0.015019190264865756, 0.007689292387415965, 0.006176682732378443 ], "state_rho": [ 0.011923154350370169, 0.9337877084811529, 0.9292550335327784, 0.9341330577929815, 0.9364036619663239, 0.9322425921758016, 0.9240961174170176, 0.9329939633607864, 0.9331585764884949, 0.9324665367603302, 0.9281178514162699 ], "credit_rho": [ 0.031667908265565835, 0.31275976697603863, 0.2433429310719172, 0.1816188059747219, 0.11667139704028766, 0.013198353117331862, 0.022044080891646445, -0.007547003333456814, -0.011566813724736372, -0.003948230994865298, 0.016950203105807304 ], "dfa_nudge": [ -0.0003799900102118651, -0.0025626374408602715, 0.0017628272374471028, -0.001205168974896272, -0.0011821148606638114, 0.0014717701512078445, -8.787959814071655e-05, -0.0006076549955954155, 0.0005303900688886642, -0.0014991160326947768, -0.0005284918782611688 ], "state_nudge": [ -0.002327537008871635, -0.34574924657742184, -0.3358767156799634, -0.33698513607184094, -0.3561149264375369, -0.33514803399642307, -0.3557068184018135, -0.3218521823485692, -0.33325668424367905, -0.34358637283245724, -0.34090926001469296 ], "credit_nudge": [ -0.014598140881086389, -0.11370646270612876, -0.09322128010292847, -0.06459770910441875, -0.04436610918492079, -0.008244700108965239, -0.00636714743450284, 0.0006991980286935965, 0.0036097665627797446, -0.0035287897723416486, -0.007594603579491377 ], "bridge_residual": [ 0.06566914729773998, 0.37236853316426277, 0.3114783614873886, 0.26258066420753795, 0.20779911428689957, 0.13781529137243828, 0.10999641008675098, 0.07969006771842639, 0.06178054213523865, 0.07378745886186759, 0.0832565538585186 ] }, "final_per_layer": { "dfa_costate_cos": [ -0.039167389273643494, -0.0378018394112587, 0.005690325051546097, -0.023073989897966385, -0.0005057593807578087, -0.014485953375697136, 0.03301015496253967, 0.04401148855686188, 0.054177843034267426, 0.03981431573629379, -0.04246171563863754, -0.0012151142582297325, 0.01963176019489765 ], "state_costate_cos": [ 0.9444395303726196, 0.9453534483909607, 0.9460644721984863, 0.9466040134429932, 0.9469730257987976, 0.9472954273223877, 0.9476633667945862, 0.9478192925453186, 0.947782576084137, 0.9473406672477722, 0.947346568107605, 0.9471475481987, 0.9466531276702881 ], "credit_costate_cos": [ 0.04752141237258911, 0.04377397149801254, 0.04051002860069275, 0.03716123104095459, 0.0350164994597435, 0.03194836527109146, 0.02999947965145111, 0.02913709171116352, 0.027683185413479805, 0.0277146864682436, 0.027703404426574707, 0.027434173971414566, 0.027843166142702103 ], "dfa_rho": [ -0.04803554713726044, 0.001050771214067936, 0.008967258036136627, -0.0271889790892601, 0.02336559258401394, -0.018210411071777344, 0.05891512706875801, 0.040720634162425995, 0.07478035986423492, 0.04802168905735016, -0.06280035525560379, -0.0254659466445446 ], "state_rho": [ 0.9311305284500122, 0.9222633838653564, 0.9287852644920349, 0.9287664890289307, 0.9245603084564209, 0.928197979927063, 0.9275168180465698, 0.9290561676025391, 0.9267844557762146, 0.927483081817627, 0.9315245151519775, 0.9313452243804932 ], "credit_rho": [ 0.05740518122911453, 0.035541512072086334, 0.002091987058520317, 0.024556485936045647, -0.006993812508881092, 0.03284040838479996, 0.012268777936697006, -0.004999782890081406, 0.014774687588214874, -0.010628825053572655, 0.05940534919500351, -0.012859531678259373 ], "dfa_nudge": [ 0.01363457553088665, 0.013758538290858269, -0.0032786596566438675, 0.010209780186414719, -0.0013850200921297073, 0.004463233053684235, -0.012735363095998764, -0.01801125332713127, -0.019914839416742325, -0.012350432574748993, 0.017156170681118965, 0.002111367881298065 ], "state_nudge": [ -0.34207087755203247, -0.3417494297027588, -0.3413676619529724, -0.3414176106452942, -0.3412688076496124, -0.34025871753692627, -0.340381920337677, -0.34054237604141235, -0.3402785062789917, -0.34061968326568604, -0.34013575315475464, -0.340819776058197 ], "credit_nudge": [ -0.012597911059856415, -0.011231275275349617, -0.009987404569983482, -0.008699672296643257, -0.007977090775966644, -0.006919408217072487, -0.006156830117106438, -0.005891043692827225, -0.00546320341527462, -0.005353953689336777, -0.005423387512564659, -0.005434062331914902 ], "bridge_residual": [ 0.10028190910816193, 0.09995798766613007, 0.09832010418176651, 0.09528136253356934, 0.09090456366539001, 0.0843343734741211, 0.07823348790407181, 0.0723348930478096, 0.06821676343679428, 0.06773027032613754, 0.06943590939044952, 0.0740470215678215 ] } }