{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.59339439868927, "min": 0.59339439868927, "max": 1.4750220775604248, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17877.787109375, "min": 17877.787109375, "max": 44746.26953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.331294447183609, "min": -0.10078973323106766, "max": 0.3692671060562134, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 87.46173095703125, "min": -24.290325164794922, "max": 98.22505187988281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0802801176905632, "min": -0.0024337111972272396, "max": 0.6193348169326782, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.193950653076172, "min": -0.6230300664901733, "max": 146.7823486328125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06933403527813058, "min": 0.06433379392269888, "max": 0.07342454007535612, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0400105291719586, "min": 0.5139717805274928, "max": 1.043076009322962, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014091526825031194, "min": 0.0005784715096195908, "max": 0.014091526825031194, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2113729023754679, "min": 0.00752012962505468, "max": 0.2113729023754679, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.566357477913332e-06, "min": 7.566357477913332e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011349536216869997, "min": 0.00011349536216869997, "max": 0.003633019388993599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252208666666668, "min": 0.10252208666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378313000000001, "min": 1.3886848, "max": 2.6110064, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026195645799999994, "min": 0.00026195645799999994, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003929346869999999, "min": 0.003929346869999999, "max": 0.12111953936000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01371990516781807, "min": 0.01371990516781807, "max": 0.5635858178138733, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20579858124256134, "min": 0.19265973567962646, "max": 3.9451005458831787, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 502.98333333333335, "min": 475.53125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30179.0, "min": 15984.0, "max": 33011.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.296946637208263, "min": -1.0000000521540642, "max": 1.296946637208263, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.81679823249578, "min": -29.798001661896706, "max": 79.56099824607372, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.296946637208263, "min": -1.0000000521540642, "max": 1.296946637208263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.81679823249578, "min": -29.798001661896706, "max": 79.56099824607372, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07194454833418908, "min": 0.06793407663894868, "max": 11.469735141843557, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.316672900051344, "min": 4.149570376612246, "max": 183.51576226949692, "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": "1728459323", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728461482" }, "total": 2158.257645931, "count": 1, "self": 0.5309468159998687, "children": { "run_training.setup": { "total": 0.08247269199998186, "count": 1, "self": 0.08247269199998186 }, "TrainerController.start_learning": { "total": 2157.644226423, "count": 1, "self": 1.3146519789975173, "children": { "TrainerController._reset_env": { "total": 3.0031322009999997, "count": 1, "self": 3.0031322009999997 }, "TrainerController.advance": { "total": 2153.2316010370027, "count": 63419, "self": 1.3539226140633218, "children": { "env_step": { "total": 1479.4252827529785, "count": 63419, "self": 1329.089322382969, "children": { "SubprocessEnvManager._take_step": { "total": 149.54423037101648, "count": 63419, "self": 4.504177315048537, "children": { "TorchPolicy.evaluate": { "total": 145.04005305596795, "count": 62554, "self": 145.04005305596795 } } }, "workers": { "total": 0.7917299989932189, "count": 63419, "self": 0.0, "children": { "worker_root": { "total": 2153.1593004869983, "count": 63419, "is_parallel": true, "self": 938.0958154710461, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029544630000089, "count": 1, "is_parallel": true, "self": 0.0008522590000268337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021022039999820663, "count": 8, "is_parallel": true, "self": 0.0021022039999820663 } } }, "UnityEnvironment.step": { "total": 0.04777057399999762, "count": 1, "is_parallel": true, "self": 0.0006668680000245786, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005133349999937309, "count": 1, "is_parallel": true, "self": 0.0005133349999937309 }, "communicator.exchange": { "total": 0.0448829859999762, "count": 1, "is_parallel": true, "self": 0.0448829859999762 }, "steps_from_proto": { "total": 0.0017073850000031143, "count": 1, "is_parallel": true, "self": 0.00041394499996272316, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012934400000403912, "count": 8, "is_parallel": true, "self": 0.0012934400000403912 } } } } } } }, "UnityEnvironment.step": { "total": 1215.0634850159522, "count": 63418, "is_parallel": true, "self": 32.77509140498478, "children": { "UnityEnvironment._generate_step_input": { "total": 22.575641430000587, "count": 63418, "is_parallel": true, "self": 22.575641430000587 }, "communicator.exchange": { "total": 1065.8998171120088, "count": 63418, "is_parallel": true, "self": 1065.8998171120088 }, "steps_from_proto": { "total": 93.8129350689581, "count": 63418, "is_parallel": true, "self": 18.899479780936502, "children": { "_process_rank_one_or_two_observation": { "total": 74.9134552880216, "count": 507344, "is_parallel": true, "self": 74.9134552880216 } } } } } } } } } } }, "trainer_advance": { "total": 672.4523956699611, "count": 63419, "self": 2.532517773931204, "children": { "process_trajectory": { "total": 126.51854886202864, "count": 63419, "self": 126.23385501102848, "children": { "RLTrainer._checkpoint": { "total": 0.28469385100015643, "count": 2, "self": 0.28469385100015643 } } }, "_update_policy": { "total": 543.4013290340013, "count": 454, "self": 306.02918540700534, "children": { "TorchPPOOptimizer.update": { "total": 237.37214362699592, "count": 22782, "self": 237.37214362699592 } } } } } } }, "trainer_threads": { "total": 1.0369999472459313e-06, "count": 1, "self": 1.0369999472459313e-06 }, "TrainerController._save_models": { "total": 0.09484016899978087, "count": 1, "self": 0.0018904229996223876, "children": { "RLTrainer._checkpoint": { "total": 0.09294974600015848, "count": 1, "self": 0.09294974600015848 } } } } } } }