{ "protocol": "road-incremental-learning-v2", "simulation": true, "physicalVehicle": false, "domain": "dry", "assistance": true, "episodes": 90, "observations": 6666, "tdUpdates": 17720, "initialFingerprint": "d11be793", "finalFingerprint": "b0de382b", "operatingFingerprint": "d11be793", "activeModelChanged": false, "lastTelemetry": { "agent": "R1", "source": "incremental-live-training", "tick": 94, "observation": [ 0.88, 0.48, 0.8, 1, 0.56, 0.52, 1, 0, -0.06337395381637574, 0.9979898506386123, 0.028698965427282747, 0.88, 1, 0.20583397603042944, 0.48, 1, 1 ], "hidden": [ 0.8798254119377793, -0.8903674020715795, -0.559755283039521, -0.06432901271249652, 0.03841040615821476, -0.8848072598363388, -0.5274526359917125, 0.8327905358548615, -0.9628814558774885, -0.6495675358803822, 0.32083303399934837, -0.18110416705530374, 0.8862454088315803, -0.7712850390345449, 0.8849117200695193, -0.9577427987273276, -0.8975818471487026, 0.0036493528692062146, -0.7044018798052567, -0.9318811707003927, 0.6004439819804559, -0.15933546136075388, -0.025748906716784065, 0.8272178454828898 ], "q": [ 5.977364533413152, 5.350514418090406, 5.992199842895615, 5.754249924810207, 5.505136401136964, 6.1944795110886774, 5.74373013200579 ], "action": 6, "reward": -18.1756328931563, "return": -8.565226300265643, "loss": 0.08326851096775656, "replay": 700, "transitions": 6666, "tdUpdates": 17720, "episodeTDUpdates": 256, "supervisedUpdates": 0, "epsilon": 0.08218402317164103, "teacherRatio": 0.08, "weightDeltaFromOperating": 7.921221538934034, "weightDeltaThisEpisode": 0.1310365640274688, "fingerprint": "b0de382b" }, "metrics": [ { "episodes": 1, "agent": "R1", "loss": 0.1402740386588144, "return": 40.927577014883866, "outcome": "arrived", "worldMSE": 0.007133781525755416, "phase": "incremental", "collisions": 0, "interventions": 7, "steps": 141, "assistance": true, "seed": 10000 }, { "episodes": 2, "agent": "R1", "loss": 0.1427081546620769, "return": -1.965150000000012, "outcome": "collision", "worldMSE": 0.009565409916374222, "phase": "incremental", "collisions": 1, "interventions": 0, "steps": 33, "assistance": true, "seed": 10037 }, { "episodes": 3, "agent": "R1", "loss": 0.19205225701302842, "return": -2.7122747479557656, "outcome": "collision", "worldMSE": 0.010357256559317948, "phase": "incremental", "collisions": 1, "interventions": 1, "steps": 37, "assistance": true, "seed": 10074 }, { "episodes": 4, "agent": "R1", "loss": 0.7328508512595019, "return": 40.29509531416957, "outcome": "arrived", "worldMSE": 0.009746673919248447, "phase": "incremental", "collisions": 0, "interventions": 8, "steps": 104, "assistance": true, "seed": 10111 }, { "episodes": 5, "agent": "R1", "loss": 0.19132277294031808, "return": 42.963888116521346, "outcome": "arrived", "worldMSE": 0.007947089176770554, "phase": "incremental", "collisions": 0, "interventions": 0, "steps": 104, "assistance": true, "seed": 10148 }, { "episodes": 6, "agent": "R1", "loss": 0.1126519461069474, "return": -2.7943750000000023, "outcome": "collision", "worldMSE": 0.009543182487566458, "phase": "incremental", "collisions": 1, "interventions": 2, "steps": 46, "assistance": true, "seed": 10185 }, { "episodes": 7, "agent": "R1", "loss": 0.3390799305478682, "return": 39.00895077535083, "outcome": "arrived", "worldMSE": 0.008834939702746817, "phase": "incremental", "collisions": 0, "interventions": 27, "steps": 101, "assistance": true, "seed": 10222 }, { "episodes": 8, "agent": "R1", "loss": 0.26526178097084124, "return": -1.9461250000000128, "outcome": "collision", "worldMSE": 0.010583263220988518, "phase": "incremental", "collisions": 1, "interventions": 0, "steps": 31, "assistance": true, "seed": 10259 }, { "episodes": 9, "agent": "R1", "loss": 0.16259171465489536, "return": 3.7064279227377384, "outcome": "collision", "worldMSE": 0.006623011549852157, "phase": "incremental", "collisions": 1, "interventions": 7, "steps": 95, "assistance": true, "seed": 10296 }, { "episodes": 10, "agent": "R1", "loss": 0.06785648385587476, "return": -3.8354978499452663, "outcome": "collision", "worldMSE": 0.008485439675490928, "phase": "incremental", "collisions": 1, "interventions": 7, "steps": 38, "assistance": true, "seed": 10333 }, { "episodes": 11, "agent": "R1", "loss": 0.19991280086773253, "return": 38.50350190581884, "outcome": "arrived", "worldMSE": 0.00884155887354364, "phase": "incremental", "collisions": 0, "interventions": 30, "steps": 103, "assistance": true, "seed": 10370 }, { "episodes": 12, "agent": "R1", "loss": 0.6258585275092112, "return": -0.8162761788496304, "outcome": "collision", "worldMSE": 0.010128762131285192, "phase": "incremental", "collisions": 1, "interventions": 2, "steps": 34, "assistance": true, "seed": 10407 }, { "episodes": 13, "agent": "R1", "loss": 0.10332599033154408, "return": -1.854852782767626, "outcome": "collision", "worldMSE": 0.013633601206460868, "phase": "incremental", "collisions": 1, "interventions": 1, "steps": 31, "assistance": true, "seed": 10444 }, { "episodes": 14, "agent": "R1", "loss": 0.2006683567341774, "return": 42.04411122574124, "outcome": "arrived", "worldMSE": 0.009932254276542481, "phase": "incremental", "collisions": 0, "interventions": 3, "steps": 105, "assistance": true, "seed": 10481 }, { "episodes": 15, "agent": "R1", "loss": 0.6837833283614311, "return": -2.694261515128261, "outcome": "collision", "worldMSE": 0.011004170381401827, "phase": "incremental", "collisions": 1, "interventions": 0, "steps": 33, "assistance": true, "seed": 10518 }, { "episodes": 16, "agent": "R1", "loss": 0.21039340339481813, "return": -3.048581366769614, "outcome": "collision", "worldMSE": 0.009634511693036061, "phase": "incremental", "collisions": 1, "interventions": 1, "steps": 37, "assistance": true, "seed": 10555 }, { "episodes": 17, "agent": "R1", "loss": 0.30719845490729336, "return": 37.36957355821717, "outcome": "arrived", "worldMSE": 0.0073076414848815, "phase": "incremental", "collisions": 0, "interventions": 32, "steps": 126, "assistance": true, "seed": 10592 }, { "episodes": 18, "agent": "R1", "loss": 0.08037708087088646, "return": 42.797239483565015, "outcome": "arrived", "worldMSE": 0.009332911344131566, "phase": "incremental", "collisions": 0, "interventions": 4, "steps": 79, "assistance": true, "seed": 10629 }, { "episodes": 19, "agent": "R1", "loss": 0.5321521760782117, "return": 42.995273506132094, "outcome": "arrived", "worldMSE": 0.007658856655183785, "phase": "incremental", "collisions": 0, "interventions": 0, "steps": 104, "assistance": true, "seed": 10666 }, { "episodes": 20, "agent": "R1", "loss": 0.4071503713922762, "return": 41.491885616717965, "outcome": "arrived", "worldMSE": 0.00827265056668911, "phase": "incremental", "collisions": 0, "interventions": 8, "steps": 105, "assistance": true, "seed": 10703 }, { "episodes": 21, "agent": "R1", "loss": 0.5573099642398406, "return": 42.619331164202876, "outcome": "arrived", "worldMSE": 0.01001970216700046, "phase": "incremental", "collisions": 0, "interventions": 1, "steps": 100, "assistance": true, "seed": 10740 }, { "episodes": 22, "agent": "R1", "loss": 0.5445505085116967, "return": 41.40890475857412, "outcome": "arrived", "worldMSE": 0.008065996593022817, "phase": "incremental", "collisions": 0, "interventions": 11, "steps": 101, "assistance": true, "seed": 10777 }, { "episodes": 23, "agent": "R1", "loss": 0.8257755722950733, "return": 42.9230731202526, "outcome": "arrived", "worldMSE": 0.008557109451483604, "phase": "incremental", "collisions": 0, "interventions": 2, "steps": 95, "assistance": true, "seed": 10814 }, { "episodes": 24, "agent": "R1", "loss": 0.7931229199477497, "return": 41.38652742751009, "outcome": "arrived", "worldMSE": 0.007132806606813934, "phase": "incremental", "collisions": 0, "interventions": 6, "steps": 129, "assistance": true, "seed": 10851 }, { "episodes": 25, "agent": "R1", "loss": 0.0799571022445383, "return": 42.46935740100978, "outcome": "arrived", "worldMSE": 0.006989844907614962, "phase": "incremental", "collisions": 0, "interventions": 0, "steps": 109, "assistance": true, "seed": 10888 }, { "episodes": 26, "agent": "R1", "loss": 0.05720202704595577, "return": 44.3664099154526, "outcome": "arrived", "worldMSE": 0.012901859853548431, "phase": "incremental", "collisions": 0, "interventions": 0, "steps": 49, "assistance": true, "seed": 10925 }, { "episodes": 27, "agent": "R1", "loss": 0.19180416553503388, "return": -4.324486379676463, "outcome": "collision", "worldMSE": 0.009645289765498931, "phase": "incremental", "collisions": 1, "interventions": 10, "steps": 49, "assistance": true, "seed": 10962 }, { "episodes": 28, "agent": "R1", "loss": 0.07423792180550695, "return": 41.064640000000026, "outcome": "arrived", "worldMSE": 0.008640239092640676, "phase": "incremental", "collisions": 0, "interventions": 12, "steps": 96, "assistance": true, "seed": 10999 }, { "episodes": 29, "agent": "R1", "loss": 0.5516195559957601, "return": 43.22500000000001, "outcome": "arrived", "worldMSE": 0.008633001695945355, "phase": "incremental", "collisions": 0, "interventions": 0, "steps": 95, "assistance": true, "seed": 11036 }, { "episodes": 30, "agent": "R1", "loss": 0.033844090298883044, "return": -4.453649948766895, "outcome": "collision", "worldMSE": 0.010742784958509551, "phase": "incremental", "collisions": 1, "interventions": 11, "steps": 38, "assistance": true, "seed": 11073 }, { "episodes": 31, "agent": "R1", "loss": 0.11907668321371857, "return": 40.13544742569538, "outcome": "arrived", "worldMSE": 0.008101073856805285, "phase": "incremental", "collisions": 0, "interventions": 15, "steps": 128, "assistance": true, "seed": 11110 }, { "episodes": 32, "agent": "R1", "loss": 0.16659586077806324, "return": 40.541371667775465, "outcome": "arrived", "worldMSE": 0.008989963521027176, "phase": "incremental", "collisions": 0, "interventions": 18, "steps": 94, "assistance": true, "seed": 11147 }, { "episodes": 33, "agent": "R1", "loss": 0.17666667983789383, "return": -3.6736949349014516, "outcome": "collision", "worldMSE": 0.008107529683104037, "phase": "incremental", "collisions": 1, "interventions": 6, "steps": 47, "assistance": true, "seed": 11184 }, { "episodes": 34, "agent": "R1", "loss": 0.06470400926656487, "return": -3.6959000000000035, "outcome": "collision", "worldMSE": 0.010624969463187736, "phase": "incremental", "collisions": 1, "interventions": 3, "steps": 29, "assistance": true, "seed": 11221 }, { "episodes": 35, "agent": "R1", "loss": 0.08535588075055159, "return": 38.59216679860936, "outcome": "arrived", "worldMSE": 0.006928215600845064, "phase": "incremental", "collisions": 0, "interventions": 26, "steps": 124, "assistance": true, "seed": 11258 }, { "episodes": 36, "agent": "R1", "loss": 0.23424688980921166, "return": 43.66720708944973, "outcome": "arrived", "worldMSE": 0.01071327868697479, "phase": "incremental", "collisions": 0, "interventions": 0, "steps": 77, "assistance": true, "seed": 11295 }, { "episodes": 37, "agent": "R1", "loss": 0.11128448818869506, "return": 37.824999999999974, "outcome": "arrived", "worldMSE": 0.008695873231017242, "phase": "incremental", "collisions": 0, "interventions": 35, "steps": 101, "assistance": true, "seed": 11332 }, { "episodes": 38, "agent": "R1", "loss": 0.11813114843271733, "return": 42.466825000000014, "outcome": "arrived", "worldMSE": 0.010142792787668305, "phase": "incremental", "collisions": 0, "interventions": 7, "steps": 78, "assistance": true, "seed": 11369 }, { "episodes": 39, "agent": "R1", "loss": 0.14189981170175323, "return": 40.67423499999998, "outcome": "arrived", "worldMSE": 0.008412512980570155, "phase": "incremental", "collisions": 0, "interventions": 17, "steps": 95, "assistance": true, "seed": 11406 }, { "episodes": 40, "agent": "R1", "loss": 0.25136137377033235, "return": -2.84612254811176, "outcome": "collision", "worldMSE": 0.008319490892573694, "phase": "incremental", "collisions": 1, "interventions": 0, "steps": 48, "assistance": true, "seed": 11443 }, { "episodes": 41, "agent": "R1", "loss": 0.10536969702771071, "return": 40.57414472694695, "outcome": "arrived", "worldMSE": 0.008354422858407816, "phase": "incremental", "collisions": 0, "interventions": 13, "steps": 116, "assistance": true, "seed": 11480 }, { "episodes": 42, "agent": "R1", "loss": 0.0839604597495078, "return": 42.80962500000006, "outcome": "arrived", "worldMSE": 0.008677306183749161, "phase": "incremental", "collisions": 0, "interventions": 0, "steps": 98, "assistance": true, "seed": 11517 }, { "episodes": 43, "agent": "R1", "loss": 0.0680115515770608, "return": -3.4629575650244657, "outcome": "collision", "worldMSE": 0.008686113095379394, "phase": "incremental", "collisions": 1, "interventions": 5, "steps": 37, "assistance": true, "seed": 11554 }, { "episodes": 44, "agent": "R1", "loss": 0.09486993301856131, "return": 40.22732821028174, "outcome": "arrived", "worldMSE": 0.008580815403020825, "phase": "incremental", "collisions": 0, "interventions": 17, "steps": 112, "assistance": true, "seed": 11591 }, { "episodes": 45, "agent": "R1", "loss": 0.06419279831944343, "return": -0.9740500000000125, "outcome": "collision", "worldMSE": 0.010036767484596766, "phase": "incremental", "collisions": 1, "interventions": 3, "steps": 32, "assistance": true, "seed": 11628 }, { "episodes": 46, "agent": "R1", "loss": 0.011932847495018667, "return": 42.19417440488612, "outcome": "arrived", "worldMSE": 0.009296644953763929, "phase": "incremental", "collisions": 0, "interventions": 7, "steps": 94, "assistance": true, "seed": 11665 }, { "episodes": 47, "agent": "R1", "loss": 0.10197629916818027, "return": -2.763850000000023, "outcome": "collision", "worldMSE": 0.008060975398720879, "phase": "incremental", "collisions": 1, "interventions": 2, "steps": 49, "assistance": true, "seed": 11702 }, { "episodes": 48, "agent": "R1", "loss": 0.0636523575429401, "return": 42.72634760737115, "outcome": "arrived", "worldMSE": 0.008101420008460772, "phase": "incremental", "collisions": 0, "interventions": 1, "steps": 102, "assistance": true, "seed": 11739 }, { "episodes": 49, "agent": "R1", "loss": 0.05704421168495016, "return": 39.423849999999995, "outcome": "arrived", "worldMSE": 0.00764683257379047, "phase": "incremental", "collisions": 0, "interventions": 24, "steps": 99, "assistance": true, "seed": 11776 }, { "episodes": 50, "agent": "R1", "loss": 0.06889989189534043, "return": 39.433505, "outcome": "arrived", "worldMSE": 0.009120253596052171, "phase": "incremental", "collisions": 0, "interventions": 26, "steps": 90, "assistance": true, "seed": 11813 }, { "episodes": 51, "agent": "R1", "loss": 0.0883993529736152, "return": 39.580743935964165, "outcome": "arrived", "worldMSE": 0.009070061432504528, "phase": "incremental", "collisions": 0, "interventions": 21, "steps": 106, "assistance": true, "seed": 11850 }, { "episodes": 52, "agent": "R1", "loss": 0.04217997820624431, "return": 39.57437499999998, "outcome": "arrived", "worldMSE": 0.009402943474962618, "phase": "incremental", "collisions": 0, "interventions": 22, "steps": 91, "assistance": true, "seed": 11887 }, { "episodes": 53, "agent": "R1", "loss": 0.06528850011902533, "return": 38.6579365333285, "outcome": "arrived", "worldMSE": 0.01005919803193169, "phase": "incremental", "collisions": 0, "interventions": 28, "steps": 89, "assistance": true, "seed": 11924 }, { "episodes": 54, "agent": "R1", "loss": 0.0922507728940876, "return": -3.8127975864411248, "outcome": "collision", "worldMSE": 0.008093371106651343, "phase": "incremental", "collisions": 1, "interventions": 6, "steps": 50, "assistance": true, "seed": 11961 }, { "episodes": 55, "agent": "R1", "loss": 0.11233382589228286, "return": -2.7618150528029464, "outcome": "collision", "worldMSE": 0.01015320775699882, "phase": "incremental", "collisions": 1, "interventions": 1, "steps": 34, "assistance": true, "seed": 11998 }, { "episodes": 56, "agent": "R1", "loss": 0.12905406375449308, "return": -3.3655572556465643, "outcome": "collision", "worldMSE": 0.008432142936530352, "phase": "incremental", "collisions": 1, "interventions": 9, "steps": 36, "assistance": true, "seed": 12035 }, { "episodes": 57, "agent": "R1", "loss": 0.109005521306276, "return": 40.23523716594123, "outcome": "arrived", "worldMSE": 0.011280210041312407, "phase": "incremental", "collisions": 0, "interventions": 16, "steps": 100, "assistance": true, "seed": 12072 }, { "episodes": 58, "agent": "R1", "loss": 0.047712514134728296, "return": -4.436446458632291, "outcome": "collision", "worldMSE": 0.00913867283584586, "phase": "incremental", "collisions": 1, "interventions": 14, "steps": 41, "assistance": true, "seed": 12109 }, { "episodes": 59, "agent": "R1", "loss": 0.5415744703037247, "return": 41.7639236942657, "outcome": "arrived", "worldMSE": 0.009150221517302768, "phase": "incremental", "collisions": 0, "interventions": 11, "steps": 85, "assistance": true, "seed": 12146 }, { "episodes": 60, "agent": "R1", "loss": 0.6535494681650557, "return": -3.601576164381056, "outcome": "collision", "worldMSE": 0.008219415930511896, "phase": "incremental", "collisions": 1, "interventions": 9, "steps": 47, "assistance": true, "seed": 12183 }, { "episodes": 61, "agent": "R1", "loss": 0.5005665222886407, "return": 37.45089279211583, "outcome": "arrived", "worldMSE": 0.007814935264934042, "phase": "incremental", "collisions": 0, "interventions": 33, "steps": 126, "assistance": true, "seed": 12220 }, { "episodes": 62, "agent": "R1", "loss": 0.055227155053649044, "return": -2.216591588217666, "outcome": "collision", "worldMSE": 0.00822646000044445, "phase": "incremental", "collisions": 1, "interventions": 4, "steps": 34, "assistance": true, "seed": 12257 }, { "episodes": 63, "agent": "R1", "loss": 0.23610333883934054, "return": -3.6592737161997153, "outcome": "collision", "worldMSE": 0.008960853391966062, "phase": "incremental", "collisions": 1, "interventions": 8, "steps": 37, "assistance": true, "seed": 12294 }, { "episodes": 64, "agent": "R1", "loss": 0.04530219761899382, "return": 37.23663600650755, "outcome": "arrived", "worldMSE": 0.009435824071892916, "phase": "incremental", "collisions": 0, "interventions": 38, "steps": 102, "assistance": true, "seed": 12331 }, { "episodes": 65, "agent": "R1", "loss": 0.03319316152801434, "return": 42.06452789653121, "outcome": "arrived", "worldMSE": 0.009956229535174657, "phase": "incremental", "collisions": 0, "interventions": 10, "steps": 72, "assistance": true, "seed": 12368 }, { "episodes": 66, "agent": "R1", "loss": 0.646035122440477, "return": -3.3806369741584863, "outcome": "collision", "worldMSE": 0.00873643434260203, "phase": "incremental", "collisions": 1, "interventions": 8, "steps": 46, "assistance": true, "seed": 12405 }, { "episodes": 67, "agent": "R1", "loss": 0.1816354142051931, "return": -3.3320750000000086, "outcome": "collision", "worldMSE": 0.011169717253221068, "phase": "incremental", "collisions": 1, "interventions": 3, "steps": 29, "assistance": true, "seed": 12442 }, { "episodes": 68, "agent": "R1", "loss": 0.1324316660517044, "return": 42.26797019784236, "outcome": "arrived", "worldMSE": 0.010009697438404496, "phase": "incremental", "collisions": 0, "interventions": 6, "steps": 87, "assistance": true, "seed": 12479 }, { "episodes": 69, "agent": "R1", "loss": 0.13095886118575106, "return": -2.6620971268437685, "outcome": "collision", "worldMSE": 0.010233904781990606, "phase": "incremental", "collisions": 1, "interventions": 7, "steps": 35, "assistance": true, "seed": 12516 }, { "episodes": 70, "agent": "R1", "loss": 0.8898242505629796, "return": -3.2833903460162137, "outcome": "collision", "worldMSE": 0.008490867982043486, "phase": "incremental", "collisions": 1, "interventions": 5, "steps": 38, "assistance": true, "seed": 12553 }, { "episodes": 71, "agent": "R1", "loss": 0.303851990304268, "return": 40.073712199720745, "outcome": "arrived", "worldMSE": 0.012487650479539704, "phase": "incremental", "collisions": 0, "interventions": 19, "steps": 105, "assistance": true, "seed": 12590 }, { "episodes": 72, "agent": "R1", "loss": 0.12174239625910058, "return": -5.44364319082859, "outcome": "collision", "worldMSE": 0.010449329622852815, "phase": "incremental", "collisions": 1, "interventions": 16, "steps": 45, "assistance": true, "seed": 12627 }, { "episodes": 73, "agent": "R1", "loss": 0.8003105330158873, "return": -3.5674518891918563, "outcome": "collision", "worldMSE": 0.008315411789310017, "phase": "incremental", "collisions": 1, "interventions": 9, "steps": 47, "assistance": true, "seed": 12664 }, { "episodes": 74, "agent": "R1", "loss": 0.878452912892944, "return": 37.498706686735225, "outcome": "arrived", "worldMSE": 0.008306152267746805, "phase": "incremental", "collisions": 0, "interventions": 36, "steps": 107, "assistance": true, "seed": 12701 }, { "episodes": 75, "agent": "R1", "loss": 0.13688762359152343, "return": 41.95802572031478, "outcome": "arrived", "worldMSE": 0.010120092493311868, "phase": "incremental", "collisions": 0, "interventions": 12, "steps": 73, "assistance": true, "seed": 12738 }, { "episodes": 76, "agent": "R1", "loss": 0.7242387407702882, "return": -3.315351605860906, "outcome": "collision", "worldMSE": 0.008997185495091474, "phase": "incremental", "collisions": 1, "interventions": 8, "steps": 35, "assistance": true, "seed": 12775 }, { "episodes": 77, "agent": "R1", "loss": 1.2489981869580915, "return": 40.54658598054823, "outcome": "arrived", "worldMSE": 0.014513129245431713, "phase": "incremental", "collisions": 0, "interventions": 17, "steps": 98, "assistance": true, "seed": 12812 }, { "episodes": 78, "agent": "R1", "loss": 0.7837210180959941, "return": -4.723064981060638, "outcome": "collision", "worldMSE": 0.011042854808286647, "phase": "incremental", "collisions": 1, "interventions": 11, "steps": 43, "assistance": true, "seed": 12849 }, { "episodes": 79, "agent": "R1", "loss": 0.6090359676825696, "return": 40.07046154832133, "outcome": "arrived", "worldMSE": 0.010532568910505354, "phase": "incremental", "collisions": 0, "interventions": 23, "steps": 82, "assistance": true, "seed": 12886 }, { "episodes": 80, "agent": "R1", "loss": 0.02854204452097832, "return": -3.6555921345505187, "outcome": "collision", "worldMSE": 0.009137125936197688, "phase": "incremental", "collisions": 1, "interventions": 9, "steps": 47, "assistance": true, "seed": 12923 }, { "episodes": 81, "agent": "R1", "loss": 0.20261438711119284, "return": -4.561335133623363, "outcome": "collision", "worldMSE": 0.010022337008091003, "phase": "incremental", "collisions": 1, "interventions": 12, "steps": 50, "assistance": true, "seed": 12960 }, { "episodes": 82, "agent": "R1", "loss": 0.43230238479517846, "return": 41.85119743801607, "outcome": "arrived", "worldMSE": 0.008461258833905172, "phase": "incremental", "collisions": 0, "interventions": 8, "steps": 100, "assistance": true, "seed": 12997 }, { "episodes": 83, "agent": "R1", "loss": 0.732721713415503, "return": -3.6855543918878357, "outcome": "collision", "worldMSE": 0.009026134907521795, "phase": "incremental", "collisions": 1, "interventions": 9, "steps": 36, "assistance": true, "seed": 13034 }, { "episodes": 84, "agent": "R1", "loss": 0.5443791646510363, "return": -2.5778559918699706, "outcome": "collision", "worldMSE": 0.012217184336327652, "phase": "incremental", "collisions": 1, "interventions": 0, "steps": 29, "assistance": true, "seed": 13071 }, { "episodes": 85, "agent": "R1", "loss": 1.5309359240377374, "return": 40.172990490921904, "outcome": "arrived", "worldMSE": 0.010329060669937608, "phase": "incremental", "collisions": 0, "interventions": 21, "steps": 79, "assistance": true, "seed": 13108 }, { "episodes": 86, "agent": "R1", "loss": 0.15328910429778492, "return": 39.48689395054075, "outcome": "arrived", "worldMSE": 0.012668194900107314, "phase": "incremental", "collisions": 0, "interventions": 25, "steps": 79, "assistance": true, "seed": 13145 }, { "episodes": 87, "agent": "R1", "loss": 0.517685023905256, "return": -3.538709575384436, "outcome": "collision", "worldMSE": 0.009088148763044049, "phase": "incremental", "collisions": 1, "interventions": 10, "steps": 48, "assistance": true, "seed": 13182 }, { "episodes": 88, "agent": "R1", "loss": 0.20667220557244365, "return": -5.584427360118163, "outcome": "collision", "worldMSE": 0.0054557678357690315, "phase": "incremental", "collisions": 1, "interventions": 13, "steps": 78, "assistance": true, "seed": 13219 }, { "episodes": 89, "agent": "R1", "loss": 0.2840011713666617, "return": 40.13140034433089, "outcome": "arrived", "worldMSE": 0.009027065512417396, "phase": "incremental", "collisions": 0, "interventions": 18, "steps": 108, "assistance": true, "seed": 13256 }, { "episodes": 90, "agent": "R1", "loss": 0.08326851096775656, "return": -8.565226300265643, "outcome": "collision", "worldMSE": 0.005807855651612363, "phase": "incremental", "collisions": 1, "interventions": 25, "steps": 94, "assistance": true, "seed": 13293 } ], "pairedTest": { "seed": 51001, "domain": "dry", "goal": [ 108, 60 ], "shield": true, "learning": false, "simulation": true, "before": { "outcome": "collision", "return": -4.308600000000034, "collisions": 1, "offroad": 0, "redViolations": 0, "interventions": 11, "steps": 50, "trace": [ { "tick": 1, "x": 12.096, "y": 60, "v": 0.4800000000000001, "heading": 0, "action": 1, "shielded": false, "reward": 0.008600000000001266 }, { "tick": 2, "x": 12.336, "y": 60, "v": 0.9600000000000002, "heading": 0, "action": 1, "shielded": false, "reward": 0.0589999999999982 }, { "tick": 3, "x": 12.72, "y": 60, "v": 1.4400000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.10940000000000011 }, { "tick": 4, "x": 13.248000000000001, "y": 60, "v": 1.9200000000000008, "heading": 0, "action": 1, "shielded": false, "reward": 0.15980000000000202 }, { "tick": 5, "x": 13.920000000000002, "y": 60, "v": 2.4000000000000012, "heading": 0, "action": 1, "shielded": false, "reward": 0.21019999999999894 }, { "tick": 6, "x": 14.736000000000002, "y": 60, "v": 2.8800000000000017, "heading": 0, "action": 1, "shielded": false, "reward": 0.26060000000000083 }, { "tick": 7, "x": 15.696000000000003, "y": 60, "v": 3.360000000000002, "heading": 0, "action": 1, "shielded": false, "reward": 0.3109999999999978 }, { "tick": 8, "x": 16.8, "y": 60, "v": 3.8400000000000025, "heading": 0, "action": 1, "shielded": false, "reward": 0.36139999999999967 }, { "tick": 9, "x": 18.048, "y": 60, "v": 4.320000000000003, "heading": 0, "action": 1, "shielded": false, "reward": 0.4118000000000016 }, { "tick": 10, "x": 19.439999999999998, "y": 60, "v": 4.800000000000003, "heading": 0, "action": 1, "shielded": false, "reward": 0.4621999999999985 }, { "tick": 11, "x": 20.975999999999996, "y": 60, "v": 5.280000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.5126000000000004 }, { "tick": 12, "x": 22.655999999999995, "y": 60, "v": 5.760000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.5629999999999974 }, { "tick": 13, "x": 24.479999999999997, "y": 60, "v": 6.240000000000005, "heading": 0, "action": 1, "shielded": false, "reward": 0.6133999999999993 }, { "tick": 14, "x": 26.447999999999997, "y": 60, "v": 6.720000000000005, "heading": 0, "action": 1, "shielded": false, "reward": 0.6638000000000012 }, { "tick": 15, "x": 28.559999999999995, "y": 60, "v": 7.2000000000000055, "heading": 0, "action": 1, "shielded": false, "reward": 0.714200000000003 }, { "tick": 16, "x": 30.815999999999995, "y": 60, "v": 7.680000000000006, "heading": 0, "action": 1, "shielded": false, "reward": 0.7646000000000001 }, { "tick": 17, "x": 33.19999999999999, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.8093999999999951 }, { "tick": 18, "x": 35.59999999999998, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 19, "x": 37.99999999999997, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 20, "x": 40.39999999999996, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 21, "x": 42.799999999999955, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 22, "x": 45.199999999999946, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 23, "x": 47.59999999999994, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 24, "x": 49.99999999999993, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 25, "x": 51.979999999999926, "y": 60, "v": 5.8999999999999995, "heading": 0, "action": 1, "shielded": true, "reward": 0.5179999999999988 }, { "tick": 26, "x": 53.329999999999934, "y": 60, "v": 3.799999999999999, "heading": 0, "action": 1, "shielded": true, "reward": 0.297500000000003 }, { "tick": 27, "x": 54.04999999999994, "y": 60, "v": 1.6999999999999984, "heading": 0, "action": 1, "shielded": true, "reward": 0.07700000000000207 }, { "tick": 28, "x": 54.17999999999994, "y": 60, "v": 0, "heading": 0, "action": 1, "shielded": true, "reward": -0.12949999999999912 }, { "tick": 29, "x": 54.17999999999994, "y": 60, "v": 0, "heading": 0, "action": 1, "shielded": true, "reward": -0.175 }, { "tick": 30, "x": 54.27599999999994, "y": 60, "v": 0.4800000000000001, "heading": 0, "action": 1, "shielded": false, "reward": 0.008599999999998782 }, { "tick": 31, "x": 54.515999999999934, "y": 60, "v": 0.9600000000000002, "heading": 0, "action": 1, "shielded": false, "reward": 0.0589999999999982 }, { "tick": 32, "x": 54.899999999999935, "y": 60, "v": 1.4400000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.10940000000000011 }, { "tick": 33, "x": 55.42799999999993, "y": 60, "v": 1.9200000000000008, "heading": 0, "action": 1, "shielded": false, "reward": 0.15979999999999953 }, { "tick": 34, "x": 55.60199999999993, "y": 60, "v": 0, "heading": 0, "action": 1, "shielded": true, "reward": -0.11410000000000017 }, { "tick": 35, "x": 55.69799999999993, "y": 60, "v": 0.4800000000000001, "heading": 0, "action": 1, "shielded": false, "reward": 0.008599999999998782 }, { "tick": 36, "x": 55.937999999999924, "y": 60, "v": 0.9600000000000002, "heading": 0, "action": 1, "shielded": false, "reward": 0.0589999999999982 }, { "tick": 37, "x": 56.321999999999925, "y": 60, "v": 1.4400000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.10940000000000011 }, { "tick": 38, "x": 56.84999999999992, "y": 60, "v": 1.9200000000000008, "heading": 0, "action": 1, "shielded": false, "reward": 0.15979999999999953 }, { "tick": 39, "x": 57.02399999999992, "y": 60, "v": 0, "heading": 0, "action": 1, "shielded": true, "reward": -0.11410000000000017 }, { "tick": 40, "x": 57.02399999999992, "y": 60, "v": 0, "heading": 0, "action": 1, "shielded": true, "reward": -0.175 }, { "tick": 41, "x": 57.11999999999992, "y": 60, "v": 0.4800000000000001, "heading": 0, "action": 1, "shielded": false, "reward": 0.008599999999998782 }, { "tick": 42, "x": 57.359999999999914, "y": 60, "v": 0.9600000000000002, "heading": 0, "action": 1, "shielded": false, "reward": 0.0589999999999982 }, { "tick": 43, "x": 57.743999999999915, "y": 60, "v": 1.4400000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.10940000000000011 }, { "tick": 44, "x": 58.27199999999991, "y": 60, "v": 1.9200000000000008, "heading": 0, "action": 1, "shielded": false, "reward": 0.15979999999999953 }, { "tick": 45, "x": 58.94399999999991, "y": 60, "v": 2.4000000000000012, "heading": 0, "action": 1, "shielded": false, "reward": 0.21019999999999894 }, { "tick": 46, "x": 59.243999999999915, "y": 60, "v": 0.3000000000000008, "heading": 0, "action": 1, "shielded": true, "reward": -0.06999999999999851 }, { "tick": 47, "x": 59.243999999999915, "y": 60, "v": 0, "heading": 0, "action": 1, "shielded": true, "reward": -0.175 }, { "tick": 48, "x": 59.243999999999915, "y": 60, "v": 0, "heading": 0, "action": 1, "shielded": true, "reward": -0.175 }, { "tick": 49, "x": 59.33999999999991, "y": 60, "v": 0.4800000000000001, "heading": 0, "action": 1, "shielded": false, "reward": 0.008599999999998782 }, { "tick": 50, "x": 59.40399999999991, "y": 60, "v": 0.6400000000000001, "heading": 0, "action": 1, "shielded": false, "reward": -18.0026 } ], "fingerprint": "d11be793" }, "candidate": { "outcome": "collision", "return": -3.8810531870153113, "collisions": 1, "offroad": 0, "redViolations": 0, "interventions": 9, "steps": 50, "trace": [ { "tick": 1, "x": 12.096, "y": 60, "v": 0.4800000000000001, "heading": 0, "action": 1, "shielded": false, "reward": 0.008600000000001266 }, { "tick": 2, "x": 12.336, "y": 60, "v": 0.9600000000000002, "heading": 0, "action": 1, "shielded": false, "reward": 0.0589999999999982 }, { "tick": 3, "x": 12.72, "y": 60, "v": 1.4400000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.10940000000000011 }, { "tick": 4, "x": 13.248000000000001, "y": 60, "v": 1.9200000000000008, "heading": 0, "action": 1, "shielded": false, "reward": 0.15980000000000202 }, { "tick": 5, "x": 13.920000000000002, "y": 60, "v": 2.4000000000000012, "heading": 0, "action": 1, "shielded": false, "reward": 0.21019999999999894 }, { "tick": 6, "x": 14.736000000000002, "y": 60, "v": 2.8800000000000017, "heading": 0, "action": 1, "shielded": false, "reward": 0.26060000000000083 }, { "tick": 7, "x": 15.696000000000003, "y": 60, "v": 3.360000000000002, "heading": 0, "action": 1, "shielded": false, "reward": 0.3109999999999978 }, { "tick": 8, "x": 16.8, "y": 60, "v": 3.8400000000000025, "heading": 0, "action": 1, "shielded": false, "reward": 0.36139999999999967 }, { "tick": 9, "x": 18.048, "y": 60, "v": 4.320000000000003, "heading": 0, "action": 1, "shielded": false, "reward": 0.4118000000000016 }, { "tick": 10, "x": 19.439999999999998, "y": 60, "v": 4.800000000000003, "heading": 0, "action": 1, "shielded": false, "reward": 0.4621999999999985 }, { "tick": 11, "x": 20.975999999999996, "y": 60, "v": 5.280000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.5126000000000004 }, { "tick": 12, "x": 22.655999999999995, "y": 60, "v": 5.760000000000004, "heading": 0, "action": 1, "shielded": false, "reward": 0.5629999999999974 }, { "tick": 13, "x": 24.479999999999997, "y": 60, "v": 6.240000000000005, "heading": 0, "action": 1, "shielded": false, "reward": 0.6133999999999993 }, { "tick": 14, "x": 26.447999999999997, "y": 60, "v": 6.720000000000005, "heading": 0, "action": 1, "shielded": false, "reward": 0.6638000000000012 }, { "tick": 15, "x": 28.559999999999995, "y": 60, "v": 7.2000000000000055, "heading": 0, "action": 1, "shielded": false, "reward": 0.714200000000003 }, { "tick": 16, "x": 30.815999999999995, "y": 60, "v": 7.680000000000006, "heading": 0, "action": 1, "shielded": false, "reward": 0.7646000000000001 }, { "tick": 17, "x": 33.19999999999999, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.8093999999999951 }, { "tick": 18, "x": 35.59999999999998, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 19, "x": 37.99999999999997, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 20, "x": 40.39999999999996, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 21, "x": 42.799999999999955, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 22, "x": 45.199999999999946, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 23, "x": 47.59999999999994, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 24, "x": 49.99999999999993, "y": 60, "v": 8, "heading": 0, "action": 1, "shielded": false, "reward": 0.814999999999997 }, { "tick": 25, "x": 51.979999999999926, "y": 60, "v": 5.8999999999999995, "heading": 0, "action": 1, "shielded": true, "reward": 0.5179999999999988 }, { "tick": 26, "x": 53.32852796870252, "y": 60.05835414985097, "v": 3.799999999999999, "heading": 0.06654312155508807, "action": 5, "shielded": true, "reward": 0.295495468459586 }, { "tick": 27, "x": 54.04631819323951, "y": 60.11464703300649, "v": 1.6999999999999984, "heading": 0.0838802262287176, "action": 5, "shielded": true, "reward": 0.07528035978992251 }, { "tick": 28, "x": 54.17582705332572, "y": 60.125936538350466, "v": 0, "heading": 0.0876148288253237, "action": 2, "shielded": true, "reward": -0.13053617863339756 }, { "tick": 29, "x": 54.17582705332572, "y": 60.125936538350466, "v": 0, "heading": 0.0876148288253237, "action": 2, "shielded": true, "reward": -0.1757141139806801 }, { "tick": 30, "x": 54.27144380497077, "y": 60.134505698328795, "v": 0.4800000000000001, "heading": 0.09015822565231184, "action": 2, "shielded": false, "reward": 0.007675637634728045 }, { "tick": 31, "x": 54.510380131241334, "y": 60.15707226623128, "v": 0.9600000000000002, "heading": 0.09613100032882022, "action": 2, "shielded": false, "reward": 0.05772305807237743 }, { "tick": 32, "x": 54.89240350399167, "y": 60.195974143281745, "v": 1.4400000000000004, "heading": 0.1041356575890179, "action": 2, "shielded": false, "reward": 0.10761687382327989 }, { "tick": 33, "x": 55.41725604783531, "y": 60.2535284664184, "v": 1.9200000000000008, "heading": 0.11175420272632791, "action": 2, "shielded": false, "reward": 0.157171765812118 }, { "tick": 34, "x": 55.59015549382502, "y": 60.273067684117024, "v": 0, "heading": 0.11273781591921316, "action": 2, "shielded": true, "reward": -0.11514141049390263 }, { "tick": 35, "x": 55.685543927554974, "y": 60.28388649326229, "v": 0.4800000000000001, "heading": 0.1130229843093114, "action": 2, "shielded": false, "reward": 0.007996621672913127 }, { "tick": 36, "x": 55.92400608957108, "y": 60.31101206462622, "v": 0.9600000000000002, "heading": 0.11338396074017608, "action": 2, "shielded": false, "reward": 0.057539570618568146 }, { "tick": 37, "x": 56.305566022052, "y": 60.354232526278395, "v": 1.4400000000000004, "heading": 0.11249876930345915, "action": 2, "shielded": false, "reward": 0.11220589980599148 }, { "tick": 38, "x": 56.82973193145659, "y": 60.417721383220865, "v": 1.9200000000000008, "heading": 0.12453865908994613, "action": 2, "shielded": false, "reward": 0.15767120829671036 }, { "tick": 39, "x": 57.00233038495105, "y": 60.43976153563975, "v": 0, "heading": 0.12766352830794186, "action": 2, "shielded": true, "reward": -0.11514192521592219 }, { "tick": 40, "x": 57.00233038495105, "y": 60.43976153563975, "v": 0, "heading": 0.12766352830794195, "action": 2, "shielded": true, "reward": -0.17544961873918274 }, { "tick": 41, "x": 57.0975354942399, "y": 60.45208974200379, "v": 0.4800000000000001, "heading": 0.12926325084298604, "action": 2, "shielded": false, "reward": 0.007833129846283385 }, { "tick": 42, "x": 57.335452568236676, "y": 60.48363955554895, "v": 0.9600000000000002, "heading": 0.1331016446112789, "action": 2, "shielded": false, "reward": 0.057734157591673795 }, { "tick": 43, "x": 57.71586506480665, "y": 60.536003269885946, "v": 1.4400000000000004, "heading": 0.13862011619271034, "action": 2, "shielded": false, "reward": 0.10756463150650344 }, { "tick": 44, "x": 58.12891023574073, "y": 60.59329785201738, "v": 1.3650000000000007, "heading": 0.13743965061525729, "action": 5, "shielded": false, "reward": 0.1192540671480461 }, { "tick": 45, "x": 58.5197305153412, "y": 60.64705419811808, "v": 1.290000000000001, "heading": 0.13631488990044013, "action": 5, "shielded": false, "reward": 0.11146456294329189 }, { "tick": 46, "x": 58.88831554551729, "y": 60.69734399900847, "v": 1.2150000000000012, "heading": 0.1352468888024488, "action": 5, "shielded": false, "reward": 0.10367524325400371 }, { "tick": 47, "x": 59.34437886219948, "y": 60.76110902121063, "v": 1.6950000000000016, "heading": 0.14074005663098593, "action": 2, "shielded": false, "reward": 0.13394950768784744 }, { "tick": 48, "x": 59.472113676189025, "y": 60.779131707506984, "v": 0, "heading": 0.1400470541035737, "action": 5, "shielded": true, "reward": -0.13054342737897187 }, { "tick": 49, "x": 59.56716523029407, "y": 60.79259280865612, "v": 0.4800000000000001, "heading": 0.14096341290609987, "action": 2, "shielded": false, "reward": 0.007929643653352357 }, { "tick": 50, "x": 59.80473492548605, "y": 60.82666061680495, "v": 0.9600000000000002, "heading": 0.14314918466533422, "action": 2, "shielded": false, "reward": -17.942307920190423 } ], "fingerprint": "b0de382b" }, "candidateAgent": "R1", "operatingFingerprint": "d11be793", "note": "동일 시드·목적지·안전 제어. 미학습 신경망 대 로컬 후보. 단일 시험으로 배포 승인하지 않음." } }