{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45312342047691345, "min": 0.45312342047691345, "max": 1.4126359224319458, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13542.953125, "min": 13542.953125, "max": 42853.72265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29960.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29960.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5085486769676208, "min": -0.08976323157548904, "max": 0.5085486769676208, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.8337860107422, "min": -21.543174743652344, "max": 138.8337860107422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.6106587648391724, "min": -0.05523677170276642, "max": 1.6106587648391724, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 439.7098388671875, "min": -14.748218536376953, "max": 439.7098388671875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07124645535244556, "min": 0.06496397565171633, "max": 0.07214075917216407, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9974503749342378, "min": 0.5296473797198225, "max": 1.0367239441062945, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.2241313061709529, "min": 0.00020159684056382426, "max": 0.2241313061709529, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 3.1378382863933405, "min": 0.0028223557678935395, "max": 3.1378382863933405, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.535411773942864e-06, "min": 7.535411773942864e-06, "max": 0.00029485350171549996, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010549576483520009, "min": 0.00010549576483520009, "max": 0.0035081471306177, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251177142857144, "min": 0.10251177142857144, "max": 0.1982845, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351648000000001, "min": 1.4351648000000001, "max": 2.5693823000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002609259657142859, "min": 0.0002609259657142859, "max": 0.00982862155, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003652963520000002, "min": 0.003652963520000002, "max": 0.11696129176999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013752668164670467, "min": 0.013752668164670467, "max": 0.5091304779052734, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1925373524427414, "min": 0.1925373524427414, "max": 4.0730438232421875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.7922077922078, "min": 361.7922077922078, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27858.0, "min": 16375.0, "max": 32861.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5862467312193536, "min": -0.9997226321889509, "max": 1.5862467312193536, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.14099830389023, "min": -30.991401597857475, "max": 122.14099830389023, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5862467312193536, "min": -0.9997226321889509, "max": 1.5862467312193536, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.14099830389023, "min": -30.991401597857475, "max": 122.14099830389023, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0522890016300507, "min": 0.0522890016300507, "max": 9.974960602600785, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.026253125513904, "min": 4.026253125513904, "max": 169.57433024421334, "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": "1691544975", "python_version": "3.9.17 (main, Jul 5 2023, 21:05:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/renatostrianese/anaconda3/envs/RenatoTF/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": "1691546497" }, "total": 1522.3088262740002, "count": 1, "self": 0.3206392110005254, "children": { "run_training.setup": { "total": 0.02925035000043863, "count": 1, "self": 0.02925035000043863 }, "TrainerController.start_learning": { "total": 1521.9589367129993, "count": 1, "self": 1.3761018438472092, "children": { "TrainerController._reset_env": { "total": 3.3895987670002796, "count": 1, "self": 3.3895987670002796 }, "TrainerController.advance": { "total": 1517.096650718151, "count": 63550, "self": 1.361308352134074, "children": { "env_step": { "total": 1000.8401751188358, "count": 63550, "self": 902.1975040446923, "children": { "SubprocessEnvManager._take_step": { "total": 97.77462586208821, "count": 63550, "self": 3.8350899726901844, "children": { "TorchPolicy.evaluate": { "total": 93.93953588939803, "count": 62551, "self": 93.93953588939803 } } }, "workers": { "total": 0.8680452120552218, "count": 63550, "self": 0.0, "children": { "worker_root": { "total": 1519.5600681218966, "count": 63550, "is_parallel": true, "self": 712.2250033952678, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022115169995231554, "count": 1, "is_parallel": true, "self": 0.0008310689991049003, "children": { "_process_rank_one_or_two_observation": { "total": 0.001380448000418255, "count": 8, "is_parallel": true, "self": 0.001380448000418255 } } }, "UnityEnvironment.step": { "total": 0.0322420560005412, "count": 1, "is_parallel": true, "self": 0.00025998999808507506, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023164000049291644, "count": 1, "is_parallel": true, "self": 0.00023164000049291644 }, "communicator.exchange": { "total": 0.03082764000100724, "count": 1, "is_parallel": true, "self": 0.03082764000100724 }, "steps_from_proto": { "total": 0.0009227860009559663, "count": 1, "is_parallel": true, "self": 0.00023912800133985002, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006836579996161163, "count": 8, "is_parallel": true, "self": 0.0006836579996161163 } } } } } } }, "UnityEnvironment.step": { "total": 807.3350647266288, "count": 63549, "is_parallel": true, "self": 26.45920644857688, "children": { "UnityEnvironment._generate_step_input": { "total": 15.637679546878644, "count": 63549, "is_parallel": true, "self": 15.637679546878644 }, "communicator.exchange": { "total": 693.5519352910087, "count": 63549, "is_parallel": true, "self": 693.5519352910087 }, "steps_from_proto": { "total": 71.68624344016462, "count": 63549, "is_parallel": true, "self": 15.637165626963906, "children": { "_process_rank_one_or_two_observation": { "total": 56.04907781320071, "count": 508392, "is_parallel": true, "self": 56.04907781320071 } } } } } } } } } } }, "trainer_advance": { "total": 514.8951672471812, "count": 63550, "self": 2.3717744022887928, "children": { "process_trajectory": { "total": 85.97077450689903, "count": 63550, "self": 85.78830737389944, "children": { "RLTrainer._checkpoint": { "total": 0.18246713299959083, "count": 2, "self": 0.18246713299959083 } } }, "_update_policy": { "total": 426.5526183379934, "count": 455, "self": 266.21230887886304, "children": { "TorchPPOOptimizer.update": { "total": 160.34030945913037, "count": 22749, "self": 160.34030945913037 } } } } } } }, "trainer_threads": { "total": 7.899998308857903e-07, "count": 1, "self": 7.899998308857903e-07 }, "TrainerController._save_models": { "total": 0.09658459400088759, "count": 1, "self": 0.0012960020012542373, "children": { "RLTrainer._checkpoint": { "total": 0.09528859199963335, "count": 1, "self": 0.09528859199963335 } } } } } } }