{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0633280277252197, "min": 1.0633280277252197, "max": 1.4710313081741333, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 32121.013671875, "min": 31659.896484375, "max": 44625.20703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.32213273644447327, "min": -0.10748473554849625, "max": 0.32213273644447327, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 82.46598052978516, "min": -25.796337127685547, "max": 82.46598052978516, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021020887419581413, "min": 0.0035402346402406693, "max": 0.37631934881210327, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.381347179412842, "min": 0.8531965613365173, "max": 89.18768310546875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06664353782452606, "min": 0.06590332438926673, "max": 0.07438081013974858, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9330095295433649, "min": 0.4921884225982832, "max": 1.0481929850260108, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011155936189707904, "min": 2.0219307619960196e-05, "max": 0.024427384138731554, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15618310665591065, "min": 0.00026285099905948257, "max": 0.17099168897112088, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.500044035708571e-05, "min": 1.500044035708571e-05, "max": 0.0005903012587593143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00021000616499919993, "min": 0.00021000616499919993, "max": 0.006763710272714998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250005714285715, "min": 0.10250005714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350008, "min": 1.3691136000000002, "max": 2.527285, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0012597785657142856, "min": 0.0012597785657142856, "max": 0.04919193307428571, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.017636899919999997, "min": 0.017636899919999997, "max": 0.5636697715, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0071165612898766994, "min": 0.0071165612898766994, "max": 0.4374392032623291, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09963186085224152, "min": 0.09963186085224152, "max": 3.0620744228363037, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 543.3207547169811, "min": 543.3207547169811, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28796.0, "min": 15984.0, "max": 33112.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1169622281812273, "min": -1.0000000521540642, "max": 1.2150617854161696, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 59.19899809360504, "min": -32.000001668930054, "max": 66.82839819788933, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1169622281812273, "min": -1.0000000521540642, "max": 1.2150617854161696, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 59.19899809360504, "min": -32.000001668930054, "max": 66.82839819788933, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0403426862978003, "min": 0.0403426862978003, "max": 9.169923763722181, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.138162373783416, "min": 2.138162373783416, "max": 146.7187802195549, "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": "1681547828", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681549808" }, "total": 1980.619609685, "count": 1, "self": 0.4746728639997855, "children": { "run_training.setup": { "total": 0.11822604200006026, "count": 1, "self": 0.11822604200006026 }, "TrainerController.start_learning": { "total": 1980.026710779, "count": 1, "self": 1.4744307480054886, "children": { "TrainerController._reset_env": { "total": 3.682597122000061, "count": 1, "self": 3.682597122000061 }, "TrainerController.advance": { "total": 1974.6360847829942, "count": 63072, "self": 1.5375564080190998, "children": { "env_step": { "total": 1342.3998613080444, "count": 63072, "self": 1227.3846589710024, "children": { "SubprocessEnvManager._take_step": { "total": 114.1294058090366, "count": 63072, "self": 5.0864980960186585, "children": { "TorchPolicy.evaluate": { "total": 109.04290771301794, "count": 62564, "self": 109.04290771301794 } } }, "workers": { "total": 0.8857965280053577, "count": 63072, "self": 0.0, "children": { "worker_root": { "total": 1974.8842744470994, "count": 63072, "is_parallel": true, "self": 865.020114672121, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001711341999907745, "count": 1, "is_parallel": true, "self": 0.0005267580008876394, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011845839990201057, "count": 8, "is_parallel": true, "self": 0.0011845839990201057 } } }, "UnityEnvironment.step": { "total": 0.04814392200023576, "count": 1, "is_parallel": true, "self": 0.0005812200001855672, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005630900000141992, "count": 1, "is_parallel": true, "self": 0.0005630900000141992 }, "communicator.exchange": { "total": 0.04526744500026325, "count": 1, "is_parallel": true, "self": 0.04526744500026325 }, "steps_from_proto": { "total": 0.001732166999772744, "count": 1, "is_parallel": true, "self": 0.0003947409995816997, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013374260001910443, "count": 8, "is_parallel": true, "self": 0.0013374260001910443 } } } } } } }, "UnityEnvironment.step": { "total": 1109.8641597749784, "count": 63071, "is_parallel": true, "self": 32.89739887397491, "children": { "UnityEnvironment._generate_step_input": { "total": 24.045738886028175, "count": 63071, "is_parallel": true, "self": 24.045738886028175 }, "communicator.exchange": { "total": 955.4890305849635, "count": 63071, "is_parallel": true, "self": 955.4890305849635 }, "steps_from_proto": { "total": 97.43199143001175, "count": 63071, "is_parallel": true, "self": 21.09615891778185, "children": { "_process_rank_one_or_two_observation": { "total": 76.3358325122299, "count": 504568, "is_parallel": true, "self": 76.3358325122299 } } } } } } } } } } }, "trainer_advance": { "total": 630.6986670669307, "count": 63072, "self": 2.4581699709556233, "children": { "process_trajectory": { "total": 111.32431491796888, "count": 63072, "self": 110.95126922496866, "children": { "RLTrainer._checkpoint": { "total": 0.37304569300022195, "count": 2, "self": 0.37304569300022195 } } }, "_update_policy": { "total": 516.9161821780062, "count": 434, "self": 326.0929588889885, "children": { "TorchPPOOptimizer.update": { "total": 190.82322328901773, "count": 22869, "self": 190.82322328901773 } } } } } } }, "trainer_threads": { "total": 1.0540002222114708e-06, "count": 1, "self": 1.0540002222114708e-06 }, "TrainerController._save_models": { "total": 0.23359707200006596, "count": 1, "self": 0.005236977000095067, "children": { "RLTrainer._checkpoint": { "total": 0.2283600949999709, "count": 1, "self": 0.2283600949999709 } } } } } } }