{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34768223762512207, "min": 0.34768223762512207, "max": 1.4243996143341064, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10547.2880859375, "min": 10420.6103515625, "max": 43210.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5336170792579651, "min": -0.07517655938863754, "max": 0.6550937294960022, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.2783203125, "min": -18.042373657226562, "max": 189.32208251953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0023097400553524494, "min": -0.005698346998542547, "max": 0.34003564715385437, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.6374882459640503, "min": -1.578442096710205, "max": 81.60855865478516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06867795282684126, "min": 0.06564903719093408, "max": 0.07247139987541097, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9614913395757777, "min": 0.4675544516145635, "max": 1.064227509079501, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011619610750187007, "min": 0.000968140879545522, "max": 0.015561234055591436, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1626745505026181, "min": 0.008713267915909697, "max": 0.2178572767782801, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.698418862464287e-06, "min": 7.698418862464287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001077778640745, "min": 0.0001077778640745, "max": 0.0036330670889777, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256610714285715, "min": 0.10256610714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359255, "min": 1.3691136000000002, "max": 2.6110223, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002663541035714286, "min": 0.0002663541035714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037289574500000006, "min": 0.0037289574500000006, "max": 0.12112112777000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008777734823524952, "min": 0.008777734823524952, "max": 0.46443772315979004, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12288828194141388, "min": 0.12288828194141388, "max": 3.2510640621185303, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.36470588235295, "min": 290.03636363636366, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30121.0, "min": 15984.0, "max": 32368.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6023813795384974, "min": -1.0000000521540642, "max": 1.6982087746753798, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.80479864031076, "min": -32.000001668930054, "max": 180.09359823167324, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6023813795384974, "min": -1.0000000521540642, "max": 1.6982087746753798, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.80479864031076, "min": -32.000001668930054, "max": 180.09359823167324, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03175097290743927, "min": 0.02790943880146105, "max": 9.706532111391425, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7305836700397776, "min": 2.606323142128531, "max": 155.3045137822628, "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": "1739953496", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739955709" }, "total": 2212.653332159, "count": 1, "self": 0.5259540709998873, "children": { "run_training.setup": { "total": 0.0325580980002087, "count": 1, "self": 0.0325580980002087 }, "TrainerController.start_learning": { "total": 2212.09481999, "count": 1, "self": 1.4017297439527283, "children": { "TrainerController._reset_env": { "total": 2.2629960419999406, "count": 1, "self": 2.2629960419999406 }, "TrainerController.advance": { "total": 2208.3429988910475, "count": 64044, "self": 1.3957468410962974, "children": { "env_step": { "total": 1527.4400162019256, "count": 64044, "self": 1374.2043567200085, "children": { "SubprocessEnvManager._take_step": { "total": 152.44545232804376, "count": 64044, "self": 4.552562040026714, "children": { "TorchPolicy.evaluate": { "total": 147.89289028801704, "count": 62557, "self": 147.89289028801704 } } }, "workers": { "total": 0.7902071538733253, "count": 64044, "self": 0.0, "children": { "worker_root": { "total": 2207.1161919799247, "count": 64044, "is_parallel": true, "self": 943.7846184439763, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026869399998759036, "count": 1, "is_parallel": true, "self": 0.0006756959996891965, "children": { "_process_rank_one_or_two_observation": { "total": 0.002011244000186707, "count": 8, "is_parallel": true, "self": 0.002011244000186707 } } }, "UnityEnvironment.step": { "total": 0.047670025000115857, "count": 1, "is_parallel": true, "self": 0.0005459319995679834, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043706300039048074, "count": 1, "is_parallel": true, "self": 0.00043706300039048074 }, "communicator.exchange": { "total": 0.04507526699990194, "count": 1, "is_parallel": true, "self": 0.04507526699990194 }, "steps_from_proto": { "total": 0.0016117630002554506, "count": 1, "is_parallel": true, "self": 0.0003862950002258003, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012254680000296503, "count": 8, "is_parallel": true, "self": 0.0012254680000296503 } } } } } } }, "UnityEnvironment.step": { "total": 1263.3315735359483, "count": 64043, "is_parallel": true, "self": 31.40987076185047, "children": { "UnityEnvironment._generate_step_input": { "total": 22.374194225008978, "count": 64043, "is_parallel": true, "self": 22.374194225008978 }, "communicator.exchange": { "total": 1115.9627872100182, "count": 64043, "is_parallel": true, "self": 1115.9627872100182 }, "steps_from_proto": { "total": 93.58472133907071, "count": 64043, "is_parallel": true, "self": 18.64596451065472, "children": { "_process_rank_one_or_two_observation": { "total": 74.93875682841599, "count": 512344, "is_parallel": true, "self": 74.93875682841599 } } } } } } } } } } }, "trainer_advance": { "total": 679.5072358480256, "count": 64044, "self": 2.788123292995806, "children": { "process_trajectory": { "total": 127.81543050603295, "count": 64044, "self": 127.61216512803276, "children": { "RLTrainer._checkpoint": { "total": 0.2032653780001965, "count": 2, "self": 0.2032653780001965 } } }, "_update_policy": { "total": 548.9036820489969, "count": 449, "self": 300.5449475690393, "children": { "TorchPPOOptimizer.update": { "total": 248.35873447995755, "count": 22788, "self": 248.35873447995755 } } } } } } }, "trainer_threads": { "total": 8.679999154992402e-07, "count": 1, "self": 8.679999154992402e-07 }, "TrainerController._save_models": { "total": 0.08709444499982055, "count": 1, "self": 0.001460355999370222, "children": { "RLTrainer._checkpoint": { "total": 0.08563408900045033, "count": 1, "self": 0.08563408900045033 } } } } } } }