{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4350883960723877, "min": 0.4324404001235962, "max": 1.4912755489349365, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13010.8837890625, "min": 12959.3740234375, "max": 45239.3359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5290033221244812, "min": -0.12324579805135727, "max": 0.5424388647079468, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.00491333007812, "min": -29.209253311157227, "max": 147.54336547851562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.040392275899648666, "min": -0.019032644107937813, "max": 0.3473716974258423, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.14826774597168, "min": -4.70106315612793, "max": 82.32709503173828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750509509592088, "min": 0.06608095133679964, "max": 0.07384289306147755, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9450713313428923, "min": 0.48841887006125323, "max": 1.0608236833781406, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014916453946652303, "min": 0.0008099279937153941, "max": 0.01690434523403556, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20883035525313223, "min": 0.007289351943438547, "max": 0.2366608332764978, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.649883164357148e-06, "min": 7.649883164357148e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010709836430100008, "min": 0.00010709836430100008, "max": 0.0032597114134296, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254992857142857, "min": 0.10254992857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435699, "min": 1.3886848, "max": 2.4436880999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026473786428571447, "min": 0.00026473786428571447, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003706330100000003, "min": 0.003706330100000003, "max": 0.10867838295999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00916774570941925, "min": 0.00916774570941925, "max": 0.49758878350257874, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1283484399318695, "min": 0.1283484399318695, "max": 3.483121395111084, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 356.01162790697674, "min": 356.01162790697674, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30617.0, "min": 15984.0, "max": 32735.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5742116093982097, "min": -1.0000000521540642, "max": 1.6087153622737298, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.38219840824604, "min": -30.999201610684395, "max": 135.38219840824604, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5742116093982097, "min": -1.0000000521540642, "max": 1.6087153622737298, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.38219840824604, "min": -30.999201610684395, "max": 135.38219840824604, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03366266166504343, "min": 0.03366266166504343, "max": 10.818454667925835, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8949889031937346, "min": 2.8012207359424792, "max": 173.09527468681335, "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": "1693554389", "python_version": "3.9.7 (default, Sep 16 2021, 13:09:58) \n[GCC 7.5.0]", "command_line_arguments": "/home/jiangchun/anaconda3/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": "1.10.1+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1693555986" }, "total": 1597.4318542261608, "count": 1, "self": 0.3214772092178464, "children": { "run_training.setup": { "total": 0.03696372173726559, "count": 1, "self": 0.03696372173726559 }, "TrainerController.start_learning": { "total": 1597.0734132952057, "count": 1, "self": 0.7875756984576583, "children": { "TrainerController._reset_env": { "total": 3.411764082033187, "count": 1, "self": 3.411764082033187 }, "TrainerController.advance": { "total": 1592.8056629616767, "count": 63750, "self": 0.7832571645267308, "children": { "env_step": { "total": 1150.3553905030712, "count": 63750, "self": 1084.260517084971, "children": { "SubprocessEnvManager._take_step": { "total": 65.58879460627213, "count": 63750, "self": 2.6724073798395693, "children": { "TorchPolicy.evaluate": { "total": 62.91638722643256, "count": 62565, "self": 62.91638722643256 } } }, "workers": { "total": 0.506078811828047, "count": 63750, "self": 0.0, "children": { "worker_root": { "total": 1595.327154382132, "count": 63750, "is_parallel": true, "self": 579.8174426136538, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002724193036556244, "count": 1, "is_parallel": true, "self": 0.0007689148187637329, "children": { "_process_rank_one_or_two_observation": { "total": 0.001955278217792511, "count": 8, "is_parallel": true, "self": 0.001955278217792511 } } }, "UnityEnvironment.step": { "total": 0.02908002119511366, "count": 1, "is_parallel": true, "self": 0.0002723792567849159, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031809788197278976, "count": 1, "is_parallel": true, "self": 0.00031809788197278976 }, "communicator.exchange": { "total": 0.027603779919445515, "count": 1, "is_parallel": true, "self": 0.027603779919445515 }, "steps_from_proto": { "total": 0.0008857641369104385, "count": 1, "is_parallel": true, "self": 0.00021926872432231903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006664954125881195, "count": 8, "is_parallel": true, "self": 0.0006664954125881195 } } } } } } }, "UnityEnvironment.step": { "total": 1015.5097117684782, "count": 63749, "is_parallel": true, "self": 16.326832023449242, "children": { "UnityEnvironment._generate_step_input": { "total": 12.345484000630677, "count": 63749, "is_parallel": true, "self": 12.345484000630677 }, "communicator.exchange": { "total": 937.1821356192231, "count": 63749, "is_parallel": true, "self": 937.1821356192231 }, "steps_from_proto": { "total": 49.65526012517512, "count": 63749, "is_parallel": true, "self": 10.709543698932976, "children": { "_process_rank_one_or_two_observation": { "total": 38.94571642624214, "count": 509992, "is_parallel": true, "self": 38.94571642624214 } } } } } } } } } } }, "trainer_advance": { "total": 441.66701529407874, "count": 63750, "self": 1.2133225873112679, "children": { "process_trajectory": { "total": 69.33656923938543, "count": 63750, "self": 69.18343849293888, "children": { "RLTrainer._checkpoint": { "total": 0.1531307464465499, "count": 2, "self": 0.1531307464465499 } } }, "_update_policy": { "total": 371.11712346738204, "count": 443, "self": 215.1911093732342, "children": { "TorchPPOOptimizer.update": { "total": 155.92601409414783, "count": 22842, "self": 155.92601409414783 } } } } } } }, "trainer_threads": { "total": 8.698552846908569e-07, "count": 1, "self": 8.698552846908569e-07 }, "TrainerController._save_models": { "total": 0.06840968318283558, "count": 1, "self": 0.000919717364013195, "children": { "RLTrainer._checkpoint": { "total": 0.06748996581882238, "count": 1, "self": 0.06748996581882238 } } } } } } }