[ { "stage": "goal", "step": 1, "loss": 1.1256178617477417 }, { "stage": "goal", "step": 20, "loss": 0.8757796287536621 }, { "stage": "goal", "step": 40, "loss": 0.4848751425743103 }, { "stage": "goal", "step": 60, "loss": 0.2024349421262741 }, { "stage": "goal", "step": 80, "loss": 0.31732437014579773 }, { "stage": "goal", "step": 100, "loss": 0.22155670821666718 }, { "stage": "goal", "step": 120, "loss": 0.32919183373451233 }, { "stage": "goal", "step": 140, "loss": 0.171668142080307 }, { "stage": "goal", "step": 160, "loss": 1.0167959928512573 }, { "stage": "goal", "step": 180, "loss": 0.8417221903800964 }, { "stage": "goal", "step": 200, "loss": 0.10604722797870636 }, { "stage": "goal", "step": 220, "loss": 0.07537326216697693 }, { "stage": "goal", "step": 240, "loss": 0.1885790228843689 }, { "stage": "goal", "step": 260, "loss": 0.06766514480113983 }, { "stage": "goal", "step": 280, "loss": 0.14665386080741882 }, { "stage": "goal", "step": 300, "loss": 0.10101648420095444 }, { "stage": "goal", "step": 320, "loss": 0.07647702097892761 }, { "stage": "goal", "step": 340, "loss": 0.08067559450864792 }, { "stage": "goal", "step": 360, "loss": 0.12979857623577118 }, { "stage": "goal", "step": 380, "loss": 0.899062991142273 }, { "stage": "goal", "step": 400, "loss": 0.12218281626701355 }, { "stage": "goal", "step": 420, "loss": 0.07381283491849899 }, { "stage": "goal", "step": 440, "loss": 0.13227435946464539 }, { "stage": "goal", "step": 460, "loss": 0.08732561767101288 }, { "stage": "goal", "step": 480, "loss": 0.09666546434164047 }, { "stage": "goal", "step": 500, "loss": 0.06472445279359818 }, { "stage": "goal", "step": 520, "loss": 0.08121205866336823 }, { "stage": "goal", "step": 540, "loss": 0.06035961955785751 }, { "stage": "goal", "step": 560, "loss": 0.07124190032482147 }, { "stage": "goal", "step": 580, "loss": 0.14373362064361572 }, { "stage": "goal", "step": 600, "loss": 0.07122757285833359 }, { "stage": "goal", "step": 620, "loss": 0.8890293836593628 }, { "stage": "goal", "step": 640, "loss": 0.062469229102134705 }, { "stage": "goal", "step": 660, "loss": 0.05835632607340813 }, { "stage": "goal", "step": 680, "loss": 0.8515450358390808 }, { "stage": "goal", "step": 700, "loss": 0.06296383589506149 }, { "stage": "goal", "step": 720, "loss": 0.06271275877952576 }, { "stage": "goal", "step": 740, "loss": 0.09368501603603363 }, { "stage": "goal", "step": 760, "loss": 0.07982345670461655 }, { "stage": "goal", "step": 780, "loss": 0.06414016336202621 }, { "stage": "goal", "step": 800, "loss": 0.08895712345838547 }, { "stage": "high_level", "step": 1, "loss": 84.32572937011719 }, { "stage": "high_level", "step": 20, "loss": -0.0 }, { "stage": "high_level", "step": 40, "loss": -0.0 }, { "stage": "high_level", "step": 60, "loss": -0.0 }, { "stage": "high_level", "step": 80, "loss": -0.0 }, { "stage": "high_level", "step": 100, "loss": -0.0 }, { "stage": "high_level", "step": 120, "loss": -0.0 }, { "stage": "high_level", "step": 140, "loss": -0.0 }, { "stage": "high_level", "step": 160, "loss": -0.0 }, { "stage": "high_level", "step": 180, "loss": -0.0 }, { "stage": "high_level", "step": 200, "loss": -0.0 }, { "stage": "policy", "step": 1, "loss": 51.165855407714844, "text_loss": 46.97157287597656, "flow_loss": 2.0971415042877197, "rtc_delay": 5, "use_goal": true, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 20, "loss": 11.228275299072266, "text_loss": 4.843214988708496, "flow_loss": 3.192530393600464, "rtc_delay": 1, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 40, "loss": 6.2679572105407715, "text_loss": 2.9056875705718994, "flow_loss": 1.681134819984436, "rtc_delay": 4, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 60, "loss": 6.005075931549072, "text_loss": 2.709343671798706, "flow_loss": 1.647866129875183, "rtc_delay": 2, "use_goal": true, "use_history": true, "include_subtask": false }, { "stage": "policy", "step": 80, "loss": 9.903374671936035, "text_loss": 2.334010362625122, "flow_loss": 3.784682273864746, "rtc_delay": 4, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 100, "loss": 5.646769046783447, "text_loss": 2.3033981323242188, "flow_loss": 1.6716854572296143, "rtc_delay": 12, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 120, "loss": 6.867326259613037, "text_loss": 1.850703239440918, "flow_loss": 2.5083115100860596, "rtc_delay": 12, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 140, "loss": 3.6174087524414062, "text_loss": 2.0811572074890137, "flow_loss": 0.7681257128715515, "rtc_delay": 11, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 160, "loss": 4.300071716308594, "text_loss": 1.9097824096679688, "flow_loss": 1.1951446533203125, "rtc_delay": 8, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 180, "loss": 8.075389862060547, "text_loss": 1.6174044609069824, "flow_loss": 3.2289929389953613, "rtc_delay": 2, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 200, "loss": 5.758746147155762, "text_loss": 1.5621910095214844, "flow_loss": 2.0982775688171387, "rtc_delay": 11, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 220, "loss": 2.9783213138580322, "text_loss": 1.389180302619934, "flow_loss": 0.7945705056190491, "rtc_delay": 11, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 240, "loss": 5.832153797149658, "text_loss": 1.4576387405395508, "flow_loss": 2.1872575283050537, "rtc_delay": 0, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 260, "loss": 3.4007065296173096, "text_loss": 0.8826411366462708, "flow_loss": 1.2590327262878418, "rtc_delay": 5, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 280, "loss": 4.018008232116699, "text_loss": 0.9588160514831543, "flow_loss": 1.529596209526062, "rtc_delay": 11, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 300, "loss": 1.492077112197876, "text_loss": 0.9946327209472656, "flow_loss": 0.24872222542762756, "rtc_delay": 9, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 320, "loss": 5.338322639465332, "text_loss": 0.8486652970314026, "flow_loss": 2.244828701019287, "rtc_delay": 8, "use_goal": true, "use_history": true, "include_subtask": false }, { "stage": "policy", "step": 340, "loss": 2.0994033813476562, "text_loss": 0.8355546593666077, "flow_loss": 0.6319243907928467, "rtc_delay": 7, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 360, "loss": 2.2518701553344727, "text_loss": 0.5455462336540222, "flow_loss": 0.8531619906425476, "rtc_delay": 10, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 380, "loss": 7.911384105682373, "text_loss": 0.6893162727355957, "flow_loss": 3.6110339164733887, "rtc_delay": 7, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 400, "loss": 2.3619725704193115, "text_loss": 0.5672968626022339, "flow_loss": 0.8973378539085388, "rtc_delay": 10, "use_goal": true, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 420, "loss": 1.233857274055481, "text_loss": 0.661384642124176, "flow_loss": 0.28623631596565247, "rtc_delay": 12, "use_goal": true, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 440, "loss": 3.295243740081787, "text_loss": 0.4776339828968048, "flow_loss": 1.4088048934936523, "rtc_delay": 9, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 460, "loss": 1.7052180767059326, "text_loss": 0.5183412432670593, "flow_loss": 0.5934383869171143, "rtc_delay": 8, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 480, "loss": 8.46796703338623, "text_loss": 0.6230667233467102, "flow_loss": 3.922450065612793, "rtc_delay": 0, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 500, "loss": 2.5979185104370117, "text_loss": 0.27633967995643616, "flow_loss": 1.1607893705368042, "rtc_delay": 1, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 520, "loss": 2.012068510055542, "text_loss": 0.30755916237831116, "flow_loss": 0.8522546291351318, "rtc_delay": 1, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 540, "loss": 5.146071910858154, "text_loss": 0.4677533805370331, "flow_loss": 2.3391592502593994, "rtc_delay": 0, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 560, "loss": 1.9480068683624268, "text_loss": 0.9942646026611328, "flow_loss": 0.476871132850647, "rtc_delay": 7, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 580, "loss": 7.889751434326172, "text_loss": 0.6651982665061951, "flow_loss": 3.612276554107666, "rtc_delay": 3, "use_goal": true, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 600, "loss": 1.454559087753296, "text_loss": 0.5516519546508789, "flow_loss": 0.4514535963535309, "rtc_delay": 11, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 620, "loss": 4.760444641113281, "text_loss": 0.3332846760749817, "flow_loss": 2.2135798931121826, "rtc_delay": 7, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 640, "loss": 6.838594913482666, "text_loss": 0.33531704545021057, "flow_loss": 3.251638889312744, "rtc_delay": 3, "use_goal": true, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 660, "loss": 4.01173210144043, "text_loss": 0.842496395111084, "flow_loss": 1.5846179723739624, "rtc_delay": 1, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 680, "loss": 5.610707759857178, "text_loss": 0.45004716515541077, "flow_loss": 2.5803303718566895, "rtc_delay": 6, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 700, "loss": 2.415992021560669, "text_loss": 0.2757202684879303, "flow_loss": 1.0701358318328857, "rtc_delay": 3, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 720, "loss": 3.6413190364837646, "text_loss": 0.15377745032310486, "flow_loss": 1.7437708377838135, "rtc_delay": 2, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 740, "loss": 2.4192750453948975, "text_loss": 0.7513293027877808, "flow_loss": 0.8339728713035583, "rtc_delay": 4, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 760, "loss": 1.3346192836761475, "text_loss": 0.2767994999885559, "flow_loss": 0.5289098620414734, "rtc_delay": 10, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 780, "loss": 2.4135358333587646, "text_loss": 0.16017527878284454, "flow_loss": 1.1266802549362183, "rtc_delay": 3, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 800, "loss": 2.966399908065796, "text_loss": 0.2566848397254944, "flow_loss": 1.3548575639724731, "rtc_delay": 3, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 820, "loss": 1.8670570850372314, "text_loss": 0.23726917803287506, "flow_loss": 0.8148939609527588, "rtc_delay": 4, "use_goal": false, "use_history": true, "include_subtask": true }, { "stage": "policy", "step": 840, "loss": 1.6185007095336914, "text_loss": 0.27975988388061523, "flow_loss": 0.6693704128265381, "rtc_delay": 5, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 860, "loss": 0.9501249194145203, "text_loss": 0.4190976619720459, "flow_loss": 0.2655136287212372, "rtc_delay": 7, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 880, "loss": 1.5665624141693115, "text_loss": 0.317945659160614, "flow_loss": 0.6243083477020264, "rtc_delay": 5, "use_goal": false, "use_history": false, "include_subtask": true }, { "stage": "policy", "step": 900, "loss": 1.8227444887161255, "text_loss": 0.32235953211784363, "flow_loss": 0.7501924633979797, "rtc_delay": 8, "use_goal": false, "use_history": true, "include_subtask": true } ]