{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3964817225933075, "min": 0.3714603781700134, "max": 1.4161570072174072, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11938.857421875, "min": 11084.3779296875, "max": 42960.5390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29889.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29889.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49740511178970337, "min": -0.09687639027833939, "max": 0.5385540127754211, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 136.28900146484375, "min": -23.4440860748291, "max": 149.17945861816406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.011348957195878029, "min": -0.011348957195878029, "max": 0.4768191874027252, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.109614372253418, "min": -3.109614372253418, "max": 113.00614929199219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06826920363421303, "min": 0.06448889277107962, "max": 0.07569878332396493, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9557688508789823, "min": 0.5298914832677545, "max": 1.0650669390064043, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01547891434051743, "min": 0.0005451975451661822, "max": 0.01547891434051743, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21670480076724402, "min": 0.00708756808716037, "max": 0.21670480076724402, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.7064974312e-06, "min": 7.7064974312e-06, "max": 0.00029523561587384284, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010789096403679999, "min": 0.00010789096403679999, "max": 0.0036338251887249994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256879999999999, "min": 0.10256879999999999, "max": 0.19841187142857142, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359631999999998, "min": 1.3888831, "max": 2.6112750000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026662312, "min": 0.00026662312, "max": 0.009841345955714285, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037327236800000006, "min": 0.0037327236800000006, "max": 0.12114637250000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015609106048941612, "min": 0.015489430166780949, "max": 0.548474133014679, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21852748095989227, "min": 0.21685202419757843, "max": 3.8393189907073975, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 365.1625, "min": 361.09638554216866, "max": 996.0967741935484, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29213.0, "min": 16688.0, "max": 34326.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5848224801011384, "min": -0.9324065040676824, "max": 1.6073928344994783, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.78579840809107, "min": -28.904601626098156, "max": 135.02099809795618, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5848224801011384, "min": -0.9324065040676824, "max": 1.6073928344994783, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.78579840809107, "min": -28.904601626098156, "max": 135.02099809795618, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.058595473809691614, "min": 0.058595473809691614, "max": 10.524737319525551, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.687637904775329, "min": 4.597298247710569, "max": 178.92053443193436, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681627331", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681629423" }, "total": 2091.680120649, "count": 1, "self": 0.4770355499999823, "children": { "run_training.setup": { "total": 0.1085756739998942, "count": 1, "self": 0.1085756739998942 }, "TrainerController.start_learning": { "total": 2091.094509425, "count": 1, "self": 1.2811323779678787, "children": { "TrainerController._reset_env": { "total": 3.8221161689998553, "count": 1, "self": 3.8221161689998553 }, "TrainerController.advance": { "total": 2085.8990290560323, "count": 63707, "self": 1.352631495046353, "children": { "env_step": { "total": 1477.700713475048, "count": 63707, "self": 1375.8108469650822, "children": { "SubprocessEnvManager._take_step": { "total": 101.10700351198079, "count": 63707, "self": 4.625225176978574, "children": { "TorchPolicy.evaluate": { "total": 96.48177833500222, "count": 62559, "self": 96.48177833500222 } } }, "workers": { "total": 0.7828629979849211, "count": 63707, "self": 0.0, "children": { "worker_root": { "total": 2086.4761986929952, "count": 63707, "is_parallel": true, "self": 817.2395403919902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015978869998889422, "count": 1, "is_parallel": true, "self": 0.000493052999900101, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011048339999888412, "count": 8, "is_parallel": true, "self": 0.0011048339999888412 } } }, "UnityEnvironment.step": { "total": 0.049701269000024695, "count": 1, "is_parallel": true, "self": 0.0005924609997691732, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004826200001843972, "count": 1, "is_parallel": true, "self": 0.0004826200001843972 }, "communicator.exchange": { "total": 0.04674107499999991, "count": 1, "is_parallel": true, "self": 0.04674107499999991 }, "steps_from_proto": { "total": 0.0018851130000712146, "count": 1, "is_parallel": true, "self": 0.000431728999956249, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014533840001149656, "count": 8, "is_parallel": true, "self": 0.0014533840001149656 } } } } } } }, "UnityEnvironment.step": { "total": 1269.236658301005, "count": 63706, "is_parallel": true, "self": 31.963562746022944, "children": { "UnityEnvironment._generate_step_input": { "total": 22.778215380037636, "count": 63706, "is_parallel": true, "self": 22.778215380037636 }, "communicator.exchange": { "total": 1122.474027804942, "count": 63706, "is_parallel": true, "self": 1122.474027804942 }, "steps_from_proto": { "total": 92.02085237000256, "count": 63706, "is_parallel": true, "self": 19.279097117788524, "children": { "_process_rank_one_or_two_observation": { "total": 72.74175525221403, "count": 509648, "is_parallel": true, "self": 72.74175525221403 } } } } } } } } } } }, "trainer_advance": { "total": 606.845684085938, "count": 63707, "self": 2.472470443935663, "children": { "process_trajectory": { "total": 102.93256589500265, "count": 63707, "self": 102.73289349100264, "children": { "RLTrainer._checkpoint": { "total": 0.19967240400001174, "count": 2, "self": 0.19967240400001174 } } }, "_update_policy": { "total": 501.44064774699973, "count": 457, "self": 320.0866044039997, "children": { "TorchPPOOptimizer.update": { "total": 181.35404334300006, "count": 22761, "self": 181.35404334300006 } } } } } } }, "trainer_threads": { "total": 9.139998837781604e-07, "count": 1, "self": 9.139998837781604e-07 }, "TrainerController._save_models": { "total": 0.09223090800014688, "count": 1, "self": 0.0013782089999949676, "children": { "RLTrainer._checkpoint": { "total": 0.09085269900015192, "count": 1, "self": 0.09085269900015192 } } } } } } }