{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1610672026872635, "min": 0.1610672026872635, "max": 1.3958783149719238, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4832.01611328125, "min": 4800.18359375, "max": 42345.36328125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999968.0, "min": 29952.0, "max": 2999968.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999968.0, "min": 29952.0, "max": 2999968.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.803946316242218, "min": -0.11501511931419373, "max": 0.8854504227638245, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 250.0272979736328, "min": -27.603628158569336, "max": 274.4896240234375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0055601587519049644, "min": -0.021379772573709488, "max": 0.49412351846694946, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.729209303855896, "min": -5.687019348144531, "max": 117.1072769165039, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06698939946945756, "min": 0.06393518265982744, "max": 0.07469997818686762, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0048409920418635, "min": 0.4860169996021399, "max": 1.1204996728030143, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016301618192422516, "min": 0.00012048335348981264, "max": 0.017922201807821347, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24452427288633774, "min": 0.0014458002418777517, "max": 0.2509108253094989, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.502146165984443e-06, "min": 1.502146165984443e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2532192489766643e-05, "min": 2.2532192489766643e-05, "max": 0.0037171893609369328, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050068222222225, "min": 0.10050068222222225, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075102333333337, "min": 1.3897045333333333, "max": 2.692610133333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.001815399999997e-05, "min": 6.001815399999997e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009002723099999995, "min": 0.0009002723099999995, "max": 0.12392240036, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007023259066045284, "min": 0.007023259066045284, "max": 0.5400155186653137, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10534888505935669, "min": 0.10195720940828323, "max": 3.780108690261841, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 225.4142857142857, "min": 196.7027027027027, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31558.0, "min": 15984.0, "max": 32346.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.746004262619785, "min": -1.0000000521540642, "max": 1.8034557742731911, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 244.4405967667699, "min": -32.000001668930054, "max": 265.1079988181591, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.746004262619785, "min": -1.0000000521540642, "max": 1.8034557742731911, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 244.4405967667699, "min": -32.000001668930054, "max": 265.1079988181591, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016346669200252757, "min": 0.015498247259677796, "max": 10.229354818351567, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.288533688035386, "min": 2.228649978467729, "max": 163.66967709362507, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686337767", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1686345619" }, "total": 7852.909529746001, "count": 1, "self": 1.1083523270017395, "children": { "run_training.setup": { "total": 0.05098003900002368, "count": 1, "self": 0.05098003900002368 }, "TrainerController.start_learning": { "total": 7851.750197379999, "count": 1, "self": 4.622660825880303, "children": { "TrainerController._reset_env": { "total": 4.598170230999585, "count": 1, "self": 4.598170230999585 }, "TrainerController.advance": { "total": 7842.367168070119, "count": 195191, "self": 4.5622472191098495, "children": { "env_step": { "total": 5832.886905750792, "count": 195191, "self": 5475.079510594067, "children": { "SubprocessEnvManager._take_step": { "total": 355.0676091313662, "count": 195191, "self": 15.383563569569105, "children": { "TorchPolicy.evaluate": { "total": 339.6840455617971, "count": 187555, "self": 339.6840455617971 } } }, "workers": { "total": 2.739786025358171, "count": 195191, "self": 0.0, "children": { "worker_root": { "total": 7833.484932713966, "count": 195191, "is_parallel": true, "self": 2738.419280764959, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001938782000252104, "count": 1, "is_parallel": true, "self": 0.0005986750006741204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013401069995779835, "count": 8, "is_parallel": true, "self": 0.0013401069995779835 } } }, "UnityEnvironment.step": { "total": 0.10721542599958411, "count": 1, "is_parallel": true, "self": 0.0006353489993671246, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005907959998694423, "count": 1, "is_parallel": true, "self": 0.0005907959998694423 }, "communicator.exchange": { "total": 0.10402987600036795, "count": 1, "is_parallel": true, "self": 0.10402987600036795 }, "steps_from_proto": { "total": 0.001959404999979597, "count": 1, "is_parallel": true, "self": 0.00036369400049807155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015957109994815255, "count": 8, "is_parallel": true, "self": 0.0015957109994815255 } } } } } } }, "UnityEnvironment.step": { "total": 5095.065651949008, "count": 195190, "is_parallel": true, "self": 104.70566532047724, "children": { "UnityEnvironment._generate_step_input": { "total": 73.08688092874036, "count": 195190, "is_parallel": true, "self": 73.08688092874036 }, "communicator.exchange": { "total": 4581.18526699601, "count": 195190, "is_parallel": true, "self": 4581.18526699601 }, "steps_from_proto": { "total": 336.0878387037801, "count": 195190, "is_parallel": true, "self": 68.20542818759577, "children": { "_process_rank_one_or_two_observation": { "total": 267.88241051618434, "count": 1561520, "is_parallel": true, "self": 267.88241051618434 } } } } } } } } } } }, "trainer_advance": { "total": 2004.918015100217, "count": 195191, "self": 8.739575824369695, "children": { "process_trajectory": { "total": 371.6067859548434, "count": 195191, "self": 370.87346722984194, "children": { "RLTrainer._checkpoint": { "total": 0.7333187250014817, "count": 6, "self": 0.7333187250014817 } } }, "_update_policy": { "total": 1624.5716533210039, "count": 1380, "self": 1047.3858371671963, "children": { "TorchPPOOptimizer.update": { "total": 577.1858161538075, "count": 68412, "self": 577.1858161538075 } } } } } } }, "trainer_threads": { "total": 1.8880000425269827e-06, "count": 1, "self": 1.8880000425269827e-06 }, "TrainerController._save_models": { "total": 0.16219636499954504, "count": 1, "self": 0.00218821599810326, "children": { "RLTrainer._checkpoint": { "total": 0.16000814900144178, "count": 1, "self": 0.16000814900144178 } } } } } } }