{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.349806547164917, "min": 0.349806547164917, "max": 1.4563781023025513, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10415.83984375, "min": 10415.83984375, "max": 44180.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5775057077407837, "min": -0.10548482090234756, "max": 0.5795166492462158, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 165.1666259765625, "min": -25.316356658935547, "max": 165.1666259765625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03202696144580841, "min": 0.0017850997392088175, "max": 0.29610657691955566, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.159710884094238, "min": 0.47305142879486084, "max": 71.65779113769531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06918503941380463, "min": 0.06610956231299436, "max": 0.07518119917693201, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9685905517932649, "min": 0.5117288717485552, "max": 1.0710794845465843, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01679382115149305, "min": 0.00021893618095739363, "max": 0.01679382115149305, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2351134961209027, "min": 0.0028461703524461173, "max": 0.24513486924600633, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.319518988764285e-06, "min": 7.319518988764285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010247326584269999, "min": 0.00010247326584269999, "max": 0.0033760849746384, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243980714285716, "min": 0.10243980714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341573000000003, "min": 1.3886848, "max": 2.4424642000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025373673357142866, "min": 0.00025373673357142866, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003552314270000001, "min": 0.003552314270000001, "max": 0.11255362384, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014430887997150421, "min": 0.014042859897017479, "max": 0.4727877974510193, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2020324319601059, "min": 0.1966000348329544, "max": 3.3095145225524902, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.74528301886795, "min": 299.74528301886795, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31773.0, "min": 15984.0, "max": 34348.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6625150751392797, "min": -1.0000000521540642, "max": 1.6625150751392797, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.22659796476364, "min": -31.995201647281647, "max": 176.22659796476364, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6625150751392797, "min": -1.0000000521540642, "max": 1.6625150751392797, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.22659796476364, "min": -31.995201647281647, "max": 176.22659796476364, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04493558130219891, "min": 0.04493558130219891, "max": 9.861752872355282, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.763171618033084, "min": 4.3316115870838985, "max": 157.78804595768452, "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": "1731440446", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731442736" }, "total": 2289.620816955, "count": 1, "self": 0.8357121679996453, "children": { "run_training.setup": { "total": 0.05608939199998986, "count": 1, "self": 0.05608939199998986 }, "TrainerController.start_learning": { "total": 2288.7290153950003, "count": 1, "self": 1.4034999669752324, "children": { "TrainerController._reset_env": { "total": 5.014188101000002, "count": 1, "self": 5.014188101000002 }, "TrainerController.advance": { "total": 2282.1887097910253, "count": 63894, "self": 1.392570656017142, "children": { "env_step": { "total": 1595.312173241022, "count": 63894, "self": 1446.3888284480468, "children": { "SubprocessEnvManager._take_step": { "total": 148.10963221197733, "count": 63894, "self": 4.595729609972295, "children": { "TorchPolicy.evaluate": { "total": 143.51390260200503, "count": 62570, "self": 143.51390260200503 } } }, "workers": { "total": 0.8137125809980148, "count": 63894, "self": 0.0, "children": { "worker_root": { "total": 2283.7533841229965, "count": 63894, "is_parallel": true, "self": 954.0354314479973, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00204482399999506, "count": 1, "is_parallel": true, "self": 0.000659320000011121, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013855039999839391, "count": 8, "is_parallel": true, "self": 0.0013855039999839391 } } }, "UnityEnvironment.step": { "total": 0.04801028399998586, "count": 1, "is_parallel": true, "self": 0.0005988659999047741, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048103700004276106, "count": 1, "is_parallel": true, "self": 0.00048103700004276106 }, "communicator.exchange": { "total": 0.04531488300000319, "count": 1, "is_parallel": true, "self": 0.04531488300000319 }, "steps_from_proto": { "total": 0.0016154980000351316, "count": 1, "is_parallel": true, "self": 0.000328175000106512, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012873229999286195, "count": 8, "is_parallel": true, "self": 0.0012873229999286195 } } } } } } }, "UnityEnvironment.step": { "total": 1329.7179526749992, "count": 63893, "is_parallel": true, "self": 32.85311128198305, "children": { "UnityEnvironment._generate_step_input": { "total": 22.96328993699899, "count": 63893, "is_parallel": true, "self": 22.96328993699899 }, "communicator.exchange": { "total": 1177.5388798530137, "count": 63893, "is_parallel": true, "self": 1177.5388798530137 }, "steps_from_proto": { "total": 96.36267160300349, "count": 63893, "is_parallel": true, "self": 19.588670078894893, "children": { "_process_rank_one_or_two_observation": { "total": 76.7740015241086, "count": 511144, "is_parallel": true, "self": 76.7740015241086 } } } } } } } } } } }, "trainer_advance": { "total": 685.4839658939864, "count": 63894, "self": 2.6168467409582945, "children": { "process_trajectory": { "total": 136.51072315302883, "count": 63894, "self": 136.23353593302852, "children": { "RLTrainer._checkpoint": { "total": 0.2771872200003145, "count": 2, "self": 0.2771872200003145 } } }, "_update_policy": { "total": 546.3563959999992, "count": 451, "self": 306.74996314398896, "children": { "TorchPPOOptimizer.update": { "total": 239.60643285601026, "count": 22809, "self": 239.60643285601026 } } } } } } }, "trainer_threads": { "total": 1.3879998732591048e-06, "count": 1, "self": 1.3879998732591048e-06 }, "TrainerController._save_models": { "total": 0.12261614799990639, "count": 1, "self": 0.0019690029998855607, "children": { "RLTrainer._checkpoint": { "total": 0.12064714500002083, "count": 1, "self": 0.12064714500002083 } } } } } } }