{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.269464373588562, "min": 0.2650339901447296, "max": 1.5006886720657349, "count": 55 }, "Pyramids.Policy.Entropy.sum": { "value": 8165.8486328125, "min": 7977.322265625, "max": 45524.890625, "count": 55 }, "Pyramids.Step.mean": { "value": 1649949.0, "min": 29952.0, "max": 1649949.0, "count": 55 }, "Pyramids.Step.sum": { "value": 1649949.0, "min": 29952.0, "max": 1649949.0, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.809245765209198, "min": -0.06885088980197906, "max": 0.809245765209198, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.9644775390625, "min": -16.59306526184082, "max": 241.9644775390625, "count": 55 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.035112764686346054, "min": -0.01266183890402317, "max": 0.25483280420303345, "count": 55 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.498716354370117, "min": -3.3047399520874023, "max": 61.66953659057617, "count": 55 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06762020323575209, "min": 0.06461597278532628, "max": 0.07387429472811896, "count": 55 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9466828453005292, "min": 0.489250494796119, "max": 1.0445018669147519, "count": 55 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013338210148504004, "min": 0.0005386727252210296, "max": 0.016421273174013807, "count": 55 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18673494207905605, "min": 0.006464072702652355, "max": 0.23411502497037873, "count": 55 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001365119544960333, "min": 0.0001365119544960333, "max": 0.00029838354339596195, "count": 55 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0019111673629444664, "min": 0.0019111673629444664, "max": 0.003982233072589033, "count": 55 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14550396666666668, "min": 0.14550396666666668, "max": 0.19946118095238097, "count": 55 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0370555333333336, "min": 1.3962282666666668, "max": 2.8274109666666667, "count": 55 }, "Pyramids.Policy.Beta.mean": { "value": 0.0045558462699999995, "min": 0.0045558462699999995, "max": 0.009946171977142856, "count": 55 }, "Pyramids.Policy.Beta.sum": { "value": 0.06378184778, "min": 0.06378184778, "max": 0.13275835557, "count": 55 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012130248360335827, "min": 0.01125478744506836, "max": 0.3685508370399475, "count": 55 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16982348263263702, "min": 0.15783996880054474, "max": 2.5798559188842773, "count": 55 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 233.5079365079365, "min": 233.5079365079365, "max": 999.0, "count": 55 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29422.0, "min": 15984.0, "max": 32327.0, "count": 55 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7664920509098068, "min": -1.0000000521540642, "max": 1.7664920509098068, "count": 55 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 222.57799841463566, "min": -31.997201651334763, "max": 222.57799841463566, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7664920509098068, "min": -1.0000000521540642, "max": 1.7664920509098068, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 222.57799841463566, "min": -31.997201651334763, "max": 222.57799841463566, "count": 55 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029243690274020153, "min": 0.029243690274020153, "max": 6.4307475266978145, "count": 55 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6847049745265394, "min": 3.3811807200836483, "max": 102.89196042716503, "count": 55 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1771949867", "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1771954044" }, "total": 4177.5134517, "count": 1, "self": 0.7402511000000231, "children": { "run_training.setup": { "total": 0.032688539999981, "count": 1, "self": 0.032688539999981 }, "TrainerController.start_learning": { "total": 4176.74051206, "count": 1, "self": 3.615948418953849, "children": { "TrainerController._reset_env": { "total": 4.283828176000043, "count": 1, "self": 4.283828176000043 }, "TrainerController.advance": { "total": 4168.672299668045, "count": 108442, "self": 3.563682548006909, "children": { "env_step": { "total": 2877.2120407600246, "count": 108442, "self": 2643.972967912051, "children": { "SubprocessEnvManager._take_step": { "total": 230.96271487799822, "count": 108442, "self": 8.335680869993212, "children": { "TorchPolicy.evaluate": { "total": 222.627034008005, "count": 105006, "self": 222.627034008005 } } }, "workers": { "total": 2.2763579699752654, "count": 108441, "self": 0.0, "children": { "worker_root": { "total": 4166.260338396049, "count": 108441, "is_parallel": true, "self": 1774.4157422859535, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00897214899998744, "count": 1, "is_parallel": true, "self": 0.006127012000206378, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028451369997810616, "count": 8, "is_parallel": true, "self": 0.0028451369997810616 } } }, "UnityEnvironment.step": { "total": 0.06351107000000411, "count": 1, "is_parallel": true, "self": 0.000558561000161717, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004927709999265062, "count": 1, "is_parallel": true, "self": 0.0004927709999265062 }, "communicator.exchange": { "total": 0.060867268999913904, "count": 1, "is_parallel": true, "self": 0.060867268999913904 }, "steps_from_proto": { "total": 0.0015924690000019837, "count": 1, "is_parallel": true, "self": 0.00037140899985388387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012210600001480998, "count": 8, "is_parallel": true, "self": 0.0012210600001480998 } } } } } } }, "UnityEnvironment.step": { "total": 2391.844596110095, "count": 108440, "is_parallel": true, "self": 62.887925377081956, "children": { "UnityEnvironment._generate_step_input": { "total": 44.14582356704125, "count": 108440, "is_parallel": true, "self": 44.14582356704125 }, "communicator.exchange": { "total": 2111.871402729024, "count": 108440, "is_parallel": true, "self": 2111.871402729024 }, "steps_from_proto": { "total": 172.93944443694795, "count": 108440, "is_parallel": true, "self": 38.400617932108275, "children": { "_process_rank_one_or_two_observation": { "total": 134.53882650483968, "count": 867520, "is_parallel": true, "self": 134.53882650483968 } } } } } } } } } } }, "trainer_advance": { "total": 1287.8965763600131, "count": 108441, "self": 7.161603354101317, "children": { "process_trajectory": { "total": 217.49613446292005, "count": 108441, "self": 217.08926000191923, "children": { "RLTrainer._checkpoint": { "total": 0.40687446100082525, "count": 3, "self": 0.40687446100082525 } } }, "_update_policy": { "total": 1063.2388385429917, "count": 773, "self": 413.9084696850158, "children": { "TorchPPOOptimizer.update": { "total": 649.3303688579759, "count": 38265, "self": 649.3303688579759 } } } } } } }, "trainer_threads": { "total": 1.920000613608863e-06, "count": 1, "self": 1.920000613608863e-06 }, "TrainerController._save_models": { "total": 0.1684338770000977, "count": 1, "self": 0.01432237900007749, "children": { "RLTrainer._checkpoint": { "total": 0.15411149800002022, "count": 1, "self": 0.15411149800002022 } } } } } } }