{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5249513983726501, "min": 0.5112396478652954, "max": 1.4028985500335693, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15773.740234375, "min": 15418.98828125, "max": 42558.33203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1137809306383133, "min": -0.1039334312081337, "max": 0.1305907517671585, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 28.10388946533203, "min": -24.94402313232422, "max": 32.386505126953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.2866363525390625, "min": -0.2866363525390625, "max": 0.3512887954711914, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -70.79917907714844, "min": -70.79917907714844, "max": 83.25544738769531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06477869082496113, "min": 0.06477869082496113, "max": 0.0732789714607269, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9069016715494558, "min": 0.4885674132724646, "max": 1.0534386849903967, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.05341186075634714, "min": 0.0001831550644067484, "max": 0.05341186075634714, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.74776605058886, "min": 0.0023810158372877294, "max": 0.74776605058886, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4092403874285675e-06, "min": 7.4092403874285675e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010372936542399995, "min": 0.00010372936542399995, "max": 0.003633005888998099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024697142857143, "min": 0.1024697142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345760000000003, "min": 1.3886848, "max": 2.6110019, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002567244571428571, "min": 0.0002567244571428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035941423999999995, "min": 0.0035941423999999995, "max": 0.12111908981000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010432736948132515, "min": 0.010166368447244167, "max": 0.3818514347076416, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1460583209991455, "min": 0.1423291563987732, "max": 2.672960042953491, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 778.7894736842105, "min": 724.3809523809524, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29594.0, "min": 15984.0, "max": 33101.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.16819469552291066, "min": -1.0000000521540642, "max": 0.5343219125416221, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 6.3913984298706055, "min": -31.99520167708397, "max": 21.907198414206505, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.16819469552291066, "min": -1.0000000521540642, "max": 0.5343219125416221, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 6.3913984298706055, "min": -31.99520167708397, "max": 21.907198414206505, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08491517413456581, "min": 0.07996052827757712, "max": 7.358174731954932, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.226776617113501, "min": 3.1184606028255075, "max": 117.73079571127892, "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": "1756169282", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756171355" }, "total": 2072.697681578, "count": 1, "self": 0.4474916660001327, "children": { "run_training.setup": { "total": 0.025783461000060015, "count": 1, "self": 0.025783461000060015 }, "TrainerController.start_learning": { "total": 2072.2244064509996, "count": 1, "self": 1.1948603259829724, "children": { "TrainerController._reset_env": { "total": 3.1000278520000393, "count": 1, "self": 3.1000278520000393 }, "TrainerController.advance": { "total": 2067.8552432900165, "count": 63258, "self": 1.2383093760131487, "children": { "env_step": { "total": 1431.759953103008, "count": 63258, "self": 1292.117198782003, "children": { "SubprocessEnvManager._take_step": { "total": 138.92958222201162, "count": 63258, "self": 4.2590542090232475, "children": { "TorchPolicy.evaluate": { "total": 134.67052801298837, "count": 62552, "self": 134.67052801298837 } } }, "workers": { "total": 0.713172098993482, "count": 63258, "self": 0.0, "children": { "worker_root": { "total": 2067.698822340007, "count": 63258, "is_parallel": true, "self": 879.7382292820082, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005924155999991854, "count": 1, "is_parallel": true, "self": 0.003821288000040113, "children": { "_process_rank_one_or_two_observation": { "total": 0.002102867999951741, "count": 8, "is_parallel": true, "self": 0.002102867999951741 } } }, "UnityEnvironment.step": { "total": 0.04824776599991765, "count": 1, "is_parallel": true, "self": 0.0006025599999475162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004781750000120155, "count": 1, "is_parallel": true, "self": 0.0004781750000120155 }, "communicator.exchange": { "total": 0.045520594999970854, "count": 1, "is_parallel": true, "self": 0.045520594999970854 }, "steps_from_proto": { "total": 0.0016464359999872613, "count": 1, "is_parallel": true, "self": 0.0003278550001368785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013185809998503828, "count": 8, "is_parallel": true, "self": 0.0013185809998503828 } } } } } } }, "UnityEnvironment.step": { "total": 1187.960593057999, "count": 63257, "is_parallel": true, "self": 31.354840296002294, "children": { "UnityEnvironment._generate_step_input": { "total": 22.092327199984084, "count": 63257, "is_parallel": true, "self": 22.092327199984084 }, "communicator.exchange": { "total": 1041.8831888600357, "count": 63257, "is_parallel": true, "self": 1041.8831888600357 }, "steps_from_proto": { "total": 92.63023670197686, "count": 63257, "is_parallel": true, "self": 18.174596513139704, "children": { "_process_rank_one_or_two_observation": { "total": 74.45564018883715, "count": 506056, "is_parallel": true, "self": 74.45564018883715 } } } } } } } } } } }, "trainer_advance": { "total": 634.8569808109952, "count": 63258, "self": 2.34059575296817, "children": { "process_trajectory": { "total": 118.74792346702736, "count": 63258, "self": 118.5397015590271, "children": { "RLTrainer._checkpoint": { "total": 0.20822190800026874, "count": 2, "self": 0.20822190800026874 } } }, "_update_policy": { "total": 513.7684615909997, "count": 448, "self": 287.7141963160087, "children": { "TorchPPOOptimizer.update": { "total": 226.05426527499094, "count": 22782, "self": 226.05426527499094 } } } } } } }, "trainer_threads": { "total": 9.030000001075678e-07, "count": 1, "self": 9.030000001075678e-07 }, "TrainerController._save_models": { "total": 0.07427408000012292, "count": 1, "self": 0.0011239189998377697, "children": { "RLTrainer._checkpoint": { "total": 0.07315016100028515, "count": 1, "self": 0.07315016100028515 } } } } } } }