{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25450700521469116, "min": 0.2513265013694763, "max": 1.425731897354126, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7716.65283203125, "min": 7531.7529296875, "max": 43251.00390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29902.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29902.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5468913912773132, "min": -0.10540304332971573, "max": 0.6365823149681091, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.48892211914062, "min": -25.296730041503906, "max": 180.7893829345703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027380799874663353, "min": 0.007756194565445185, "max": 0.40319085121154785, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.584481716156006, "min": 2.1019287109375, "max": 95.55622863769531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06598515946857837, "min": 0.06474892868610162, "max": 0.07235195697878317, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9897773920286757, "min": 0.5616991292927818, "max": 1.0584658651422096, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017123018421019275, "min": 0.00023954040768810967, "max": 0.017123018421019275, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25684527631528914, "min": 0.0033535657076335353, "max": 0.25684527631528914, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.443477518873336e-06, "min": 7.443477518873336e-06, "max": 0.000295215076594975, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011165216278310004, "min": 0.00011165216278310004, "max": 0.0036090342969886, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248112666666669, "min": 0.10248112666666669, "max": 0.19840502499999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372169000000002, "min": 1.4776296000000002, "max": 2.5725222000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025786455400000013, "min": 0.00025786455400000013, "max": 0.0098406619975, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003867968310000002, "min": 0.003867968310000002, "max": 0.12031083886000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014584985561668873, "min": 0.014120169915258884, "max": 0.5579977035522461, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21877478063106537, "min": 0.19768238067626953, "max": 4.463981628417969, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.7956989247312, "min": 285.9, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30578.0, "min": 15934.0, "max": 33048.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5599412869500078, "min": -0.9998000515624881, "max": 1.6929050364879648, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 143.5145983994007, "min": -31.99360164999962, "max": 167.5975986123085, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5599412869500078, "min": -0.9998000515624881, "max": 1.6929050364879648, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 143.5145983994007, "min": -31.99360164999962, "max": 167.5975986123085, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0500471337480754, "min": 0.04836135261516896, "max": 12.475103815086186, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.604336304822937, "min": 4.1674862858781125, "max": 199.60166104137897, "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": "1708911350", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708914527" }, "total": 3177.1321454090003, "count": 1, "self": 0.6001731570004267, "children": { "run_training.setup": { "total": 0.06533630900003118, "count": 1, "self": 0.06533630900003118 }, "TrainerController.start_learning": { "total": 3176.466635943, "count": 1, "self": 2.178739297989523, "children": { "TrainerController._reset_env": { "total": 4.414482060999944, "count": 1, "self": 4.414482060999944 }, "TrainerController.advance": { "total": 3169.7864719760105, "count": 64068, "self": 2.5467041879733188, "children": { "env_step": { "total": 2130.257791092021, "count": 64068, "self": 1969.038138135983, "children": { "SubprocessEnvManager._take_step": { "total": 159.8559913420636, "count": 64068, "self": 6.671488224062955, "children": { "TorchPolicy.evaluate": { "total": 153.18450311800063, "count": 62550, "self": 153.18450311800063 } } }, "workers": { "total": 1.3636616139742728, "count": 64068, "self": 0.0, "children": { "worker_root": { "total": 3170.7778017090354, "count": 64068, "is_parallel": true, "self": 1367.4470129960123, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007462790999966273, "count": 1, "is_parallel": true, "self": 0.005348088999880929, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021147020000853445, "count": 8, "is_parallel": true, "self": 0.0021147020000853445 } } }, "UnityEnvironment.step": { "total": 0.06342643000004955, "count": 1, "is_parallel": true, "self": 0.0007525450000684941, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005173430000695589, "count": 1, "is_parallel": true, "self": 0.0005173430000695589 }, "communicator.exchange": { "total": 0.0600727989999541, "count": 1, "is_parallel": true, "self": 0.0600727989999541 }, "steps_from_proto": { "total": 0.002083742999957394, "count": 1, "is_parallel": true, "self": 0.000438400999996702, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016453419999606922, "count": 8, "is_parallel": true, "self": 0.0016453419999606922 } } } } } } }, "UnityEnvironment.step": { "total": 1803.3307887130231, "count": 64067, "is_parallel": true, "self": 47.36134188999449, "children": { "UnityEnvironment._generate_step_input": { "total": 27.392768350986103, "count": 64067, "is_parallel": true, "self": 27.392768350986103 }, "communicator.exchange": { "total": 1600.4127628180036, "count": 64067, "is_parallel": true, "self": 1600.4127628180036 }, "steps_from_proto": { "total": 128.1639156540391, "count": 64067, "is_parallel": true, "self": 26.994489046058447, "children": { "_process_rank_one_or_two_observation": { "total": 101.16942660798065, "count": 512536, "is_parallel": true, "self": 101.16942660798065 } } } } } } } } } } }, "trainer_advance": { "total": 1036.9819766960163, "count": 64068, "self": 4.510689651992379, "children": { "process_trajectory": { "total": 158.17156564502625, "count": 64068, "self": 157.95296877902615, "children": { "RLTrainer._checkpoint": { "total": 0.2185968660000981, "count": 2, "self": 0.2185968660000981 } } }, "_update_policy": { "total": 874.2997213989977, "count": 456, "self": 350.3324504190109, "children": { "TorchPPOOptimizer.update": { "total": 523.9672709799868, "count": 22764, "self": 523.9672709799868 } } } } } } }, "trainer_threads": { "total": 1.1319998520775698e-06, "count": 1, "self": 1.1319998520775698e-06 }, "TrainerController._save_models": { "total": 0.08694147599999269, "count": 1, "self": 0.0019458599999779835, "children": { "RLTrainer._checkpoint": { "total": 0.0849956160000147, "count": 1, "self": 0.0849956160000147 } } } } } } }