{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29789021611213684, "min": 0.29789021611213684, "max": 1.367859959602356, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8927.173828125, "min": 8927.173828125, "max": 41495.3984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4172821640968323, "min": -0.09637138247489929, "max": 0.4753468632698059, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.57977294921875, "min": -23.22550392150879, "max": 127.39295959472656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01254123356193304, "min": 0.01254123356193304, "max": 0.5868200063705444, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3234269618988037, "min": 3.3234269618988037, "max": 139.0763397216797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06969978085373227, "min": 0.06552618757951403, "max": 0.07309274904599349, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9757969319522518, "min": 0.5101009684204372, "max": 1.0511480932473205, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013070763274574822, "min": 0.00024218573646627502, "max": 0.01475173796227734, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1829906858440475, "min": 0.003148414574061575, "max": 0.20652433147188276, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.627683171757142e-06, "min": 7.627683171757142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001067875644046, "min": 0.0001067875644046, "max": 0.0034927333357556, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254252857142857, "min": 0.10254252857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355954, "min": 1.3886848, "max": 2.5273532000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002639986042857143, "min": 0.0002639986042857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369598046, "min": 0.00369598046, "max": 0.11643801556, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03089161030948162, "min": 0.030175942927598953, "max": 0.6546319723129272, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4324825406074524, "min": 0.42246320843696594, "max": 4.582423686981201, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 419.1029411764706, "min": 405.5974025974026, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28499.0, "min": 15984.0, "max": 33026.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3798144760987032, "min": -1.0000000521540642, "max": 1.4349420881389003, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 95.20719885081053, "min": -31.99480164051056, "max": 109.05559869855642, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3798144760987032, "min": -1.0000000521540642, "max": 1.4349420881389003, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 95.20719885081053, "min": -31.99480164051056, "max": 109.05559869855642, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13095148351968036, "min": 0.12661478602508155, "max": 13.344655025750399, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 9.035652362857945, "min": 9.035652362857945, "max": 213.51448041200638, "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": "1697096574", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697098956" }, "total": 2381.92797918, "count": 1, "self": 0.5345633160000034, "children": { "run_training.setup": { "total": 0.04264655199995104, "count": 1, "self": 0.04264655199995104 }, "TrainerController.start_learning": { "total": 2381.350769312, "count": 1, "self": 1.8312415618911473, "children": { "TrainerController._reset_env": { "total": 3.01589892300035, "count": 1, "self": 3.01589892300035 }, "TrainerController.advance": { "total": 2376.420788169108, "count": 63573, "self": 1.8256890939628647, "children": { "env_step": { "total": 1717.844125627993, "count": 63573, "self": 1568.1376008410944, "children": { "SubprocessEnvManager._take_step": { "total": 148.62241601598453, "count": 63573, "self": 5.393495830064694, "children": { "TorchPolicy.evaluate": { "total": 143.22892018591983, "count": 62579, "self": 143.22892018591983 } } }, "workers": { "total": 1.0841087709140993, "count": 63573, "self": 0.0, "children": { "worker_root": { "total": 2375.8104885870443, "count": 63573, "is_parallel": true, "self": 949.8809644030521, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022297059999800695, "count": 1, "is_parallel": true, "self": 0.000690978999955405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015387270000246644, "count": 8, "is_parallel": true, "self": 0.0015387270000246644 } } }, "UnityEnvironment.step": { "total": 0.055314415999873745, "count": 1, "is_parallel": true, "self": 0.0006212250000316999, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005543299998862494, "count": 1, "is_parallel": true, "self": 0.0005543299998862494 }, "communicator.exchange": { "total": 0.0522933990000638, "count": 1, "is_parallel": true, "self": 0.0522933990000638 }, "steps_from_proto": { "total": 0.0018454619998919952, "count": 1, "is_parallel": true, "self": 0.00041616599992266856, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014292959999693267, "count": 8, "is_parallel": true, "self": 0.0014292959999693267 } } } } } } }, "UnityEnvironment.step": { "total": 1425.9295241839923, "count": 63572, "is_parallel": true, "self": 37.55473791382292, "children": { "UnityEnvironment._generate_step_input": { "total": 26.571704254092765, "count": 63572, "is_parallel": true, "self": 26.571704254092765 }, "communicator.exchange": { "total": 1249.7388750450696, "count": 63572, "is_parallel": true, "self": 1249.7388750450696 }, "steps_from_proto": { "total": 112.06420697100702, "count": 63572, "is_parallel": true, "self": 24.25149092707761, "children": { "_process_rank_one_or_two_observation": { "total": 87.81271604392941, "count": 508576, "is_parallel": true, "self": 87.81271604392941 } } } } } } } } } } }, "trainer_advance": { "total": 656.7509734471523, "count": 63573, "self": 3.1832876372186547, "children": { "process_trajectory": { "total": 131.0972472149324, "count": 63573, "self": 130.9019858219317, "children": { "RLTrainer._checkpoint": { "total": 0.1952613930006919, "count": 2, "self": 0.1952613930006919 } } }, "_update_policy": { "total": 522.4704385950013, "count": 452, "self": 313.2950051690591, "children": { "TorchPPOOptimizer.update": { "total": 209.17543342594217, "count": 22806, "self": 209.17543342594217 } } } } } } }, "trainer_threads": { "total": 1.0140001904801466e-06, "count": 1, "self": 1.0140001904801466e-06 }, "TrainerController._save_models": { "total": 0.08283964400015975, "count": 1, "self": 0.001403623999976844, "children": { "RLTrainer._checkpoint": { "total": 0.08143602000018291, "count": 1, "self": 0.08143602000018291 } } } } } } }