{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27607762813568115, "min": 0.24586544930934906, "max": 1.4860436916351318, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 5495.048828125, "min": 4933.04443359375, "max": 29863.533203125, "count": 50 }, "Pyramids.Step.mean": { "value": 999890.0, "min": 19968.0, "max": 999890.0, "count": 50 }, "Pyramids.Step.sum": { "value": 999890.0, "min": 19968.0, "max": 999890.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6114235520362854, "min": -0.07502932846546173, "max": 0.6669875383377075, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.11335754394531, "min": -12.004693031311035, "max": 124.05967712402344, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.039064064621925354, "min": 0.0345841683447361, "max": 1.9643781185150146, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.226851940155029, "min": 6.432655334472656, "max": 314.3005065917969, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06856900762667303, "min": 0.06283093447348585, "max": 0.07372255274638248, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6856900762667304, "min": 0.2948902109855299, "max": 0.7142337102388197, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015695929414405507, "min": 0.0009867582092490793, "max": 0.2095112097462982, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15695929414405507, "min": 0.008880823883241714, "max": 0.8380448389851928, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.0703589765800004e-06, "min": 3.0703589765800004e-06, "max": 0.0002969568010144, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.0703589765800006e-05, "min": 3.0703589765800006e-05, "max": 0.0025507324497558996, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10102342, "min": 0.10102342, "max": 0.19898559999999998, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.0102342, "min": 0.7959423999999999, "max": 1.8502441000000003, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011223965800000003, "min": 0.00011223965800000003, "max": 0.00989866144, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0011223965800000004, "min": 0.0011223965800000004, "max": 0.08503938559, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.05083625391125679, "min": 0.04953589662909508, "max": 3.5884857177734375, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.5083625316619873, "min": 0.445823073387146, "max": 14.35394287109375, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.23809523809524, "min": 261.9861111111111, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 19671.0, "min": 15984.0, "max": 28879.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5963406036607921, "min": -1.0000000521540642, "max": 1.7192698371788813, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 102.1657986342907, "min": -20.905201599001884, "max": 123.13639903068542, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5963406036607921, "min": -1.0000000521540642, "max": 1.7192698371788813, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 102.1657986342907, "min": -20.905201599001884, "max": 123.13639903068542, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.16292411482936586, "min": 0.1494339367491193, "max": 56.01273512840271, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 10.427143349079415, "min": 9.75880633178167, "max": 896.2037620544434, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1780402166", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1780404736" }, "total": 2569.8803703600006, "count": 1, "self": 0.47836302100040484, "children": { "run_training.setup": { "total": 0.02345482400050969, "count": 1, "self": 0.02345482400050969 }, "TrainerController.start_learning": { "total": 2569.3785525149997, "count": 1, "self": 1.5023615441386937, "children": { "TrainerController._reset_env": { "total": 2.1729307380001046, "count": 1, "self": 2.1729307380001046 }, "TrainerController.advance": { "total": 2565.620878907862, "count": 64143, "self": 1.5137652785351747, "children": { "env_step": { "total": 1897.8961897731388, "count": 64143, "self": 1734.042907747803, "children": { "SubprocessEnvManager._take_step": { "total": 163.0017928205407, "count": 64143, "self": 4.970953029694101, "children": { "TorchPolicy.evaluate": { "total": 158.03083979084658, "count": 62560, "self": 158.03083979084658 } } }, "workers": { "total": 0.8514892047951435, "count": 64143, "self": 0.0, "children": { "worker_root": { "total": 2563.6564446219427, "count": 64143, "is_parallel": true, "self": 955.885842605805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002260352000121202, "count": 1, "is_parallel": true, "self": 0.0007410460011669784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015193059989542235, "count": 8, "is_parallel": true, "self": 0.0015193059989542235 } } }, "UnityEnvironment.step": { "total": 0.10752102400056174, "count": 1, "is_parallel": true, "self": 0.0005880640001123538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005247220005912823, "count": 1, "is_parallel": true, "self": 0.0005247220005912823 }, "communicator.exchange": { "total": 0.10360907199992653, "count": 1, "is_parallel": true, "self": 0.10360907199992653 }, "steps_from_proto": { "total": 0.0027991659999315743, "count": 1, "is_parallel": true, "self": 0.00040797600013320334, "children": { "_process_rank_one_or_two_observation": { "total": 0.002391189999798371, "count": 8, "is_parallel": true, "self": 0.002391189999798371 } } } } } } }, "UnityEnvironment.step": { "total": 1607.7706020161377, "count": 64142, "is_parallel": true, "self": 35.83594821573479, "children": { "UnityEnvironment._generate_step_input": { "total": 25.398353048119134, "count": 64142, "is_parallel": true, "self": 25.398353048119134 }, "communicator.exchange": { "total": 1428.15167721311, "count": 64142, "is_parallel": true, "self": 1428.15167721311 }, "steps_from_proto": { "total": 118.38462353917384, "count": 64142, "is_parallel": true, "self": 24.316188953881465, "children": { "_process_rank_one_or_two_observation": { "total": 94.06843458529238, "count": 513136, "is_parallel": true, "self": 94.06843458529238 } } } } } } } } } } }, "trainer_advance": { "total": 666.210923856188, "count": 64143, "self": 2.8341005002876045, "children": { "process_trajectory": { "total": 131.36757172290345, "count": 64143, "self": 131.1819286509035, "children": { "RLTrainer._checkpoint": { "total": 0.185643071999948, "count": 2, "self": 0.185643071999948 } } }, "_update_policy": { "total": 532.0092516329969, "count": 461, "self": 286.6405430331115, "children": { "TorchPPOOptimizer.update": { "total": 245.3687085998854, "count": 22785, "self": 245.3687085998854 } } } } } } }, "trainer_threads": { "total": 1.0349995136493817e-06, "count": 1, "self": 1.0349995136493817e-06 }, "TrainerController._save_models": { "total": 0.08238028999949165, "count": 1, "self": 0.00112524799988023, "children": { "RLTrainer._checkpoint": { "total": 0.08125504199961142, "count": 1, "self": 0.08125504199961142 } } } } } } }