{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3206157088279724, "min": 0.32021746039390564, "max": 1.4969273805618286, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9715.9384765625, "min": 9519.4248046875, "max": 45410.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29962.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29962.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6253999471664429, "min": -0.10757457464933395, "max": 0.6515991687774658, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.23898315429688, "min": -25.81789779663086, "max": 189.6153564453125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02904333733022213, "min": -0.008796537294983864, "max": 0.16893044114112854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.277351379394531, "min": -2.392658233642578, "max": 40.543304443359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06510824000739997, "min": 0.06400309069500683, "max": 0.07389518441098167, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9115153601035996, "min": 0.5911614752878533, "max": 1.0464047590594774, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01548430218598261, "min": 0.0005122963272211974, "max": 0.016082287501149678, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21678023060375654, "min": 0.007172148581096763, "max": 0.2357938977206062, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.779204549821427e-06, "min": 7.779204549821427e-06, "max": 0.00029485327671557496, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010890886369749998, "min": 0.00010890886369749998, "max": 0.0033793604735465996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259303571428571, "min": 0.10259303571428571, "max": 0.19828442500000001, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4363025, "min": 1.4363025, "max": 2.5264534000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002690442678571428, "min": 0.0002690442678571428, "max": 0.0098286140575, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037666197499999993, "min": 0.0037666197499999993, "max": 0.11267269465999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01312094647437334, "min": 0.01312094647437334, "max": 0.31183338165283203, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18369324505329132, "min": 0.18369324505329132, "max": 2.4946670532226562, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 300.82828282828285, "min": 296.55445544554453, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29782.0, "min": 16377.0, "max": 33224.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.658753518730101, "min": -0.9999750521965325, "max": 1.6932783340363158, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 164.21659835428, "min": -31.99920167028904, "max": 166.0469985306263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.658753518730101, "min": -0.9999750521965325, "max": 1.6932783340363158, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 164.21659835428, "min": -31.99920167028904, "max": 166.0469985306263, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040827504855935164, "min": 0.040827504855935164, "max": 6.552657259956879, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.041922980737581, "min": 4.041922980737581, "max": 111.39517341926694, "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": "1704967791", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704970091" }, "total": 2299.46336148, "count": 1, "self": 0.4763794929995129, "children": { "run_training.setup": { "total": 0.05701916699990761, "count": 1, "self": 0.05701916699990761 }, "TrainerController.start_learning": { "total": 2298.9299628200006, "count": 1, "self": 1.4238685660575356, "children": { "TrainerController._reset_env": { "total": 1.98091042499982, "count": 1, "self": 1.98091042499982 }, "TrainerController.advance": { "total": 2295.4390408779436, "count": 63913, "self": 1.4846470530437728, "children": { "env_step": { "total": 1670.509673892977, "count": 63913, "self": 1538.7398123749404, "children": { "SubprocessEnvManager._take_step": { "total": 130.92771622001464, "count": 63913, "self": 4.741195245010658, "children": { "TorchPolicy.evaluate": { "total": 126.18652097500399, "count": 62558, "self": 126.18652097500399 } } }, "workers": { "total": 0.8421452980219328, "count": 63913, "self": 0.0, "children": { "worker_root": { "total": 2293.4965142380697, "count": 63913, "is_parallel": true, "self": 876.6653904871423, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017616560003261839, "count": 1, "is_parallel": true, "self": 0.0005985139996482758, "children": { "_process_rank_one_or_two_observation": { "total": 0.001163142000677908, "count": 8, "is_parallel": true, "self": 0.001163142000677908 } } }, "UnityEnvironment.step": { "total": 0.05131750900000043, "count": 1, "is_parallel": true, "self": 0.0006226690006769786, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045917599982203683, "count": 1, "is_parallel": true, "self": 0.00045917599982203683 }, "communicator.exchange": { "total": 0.04847028999984104, "count": 1, "is_parallel": true, "self": 0.04847028999984104 }, "steps_from_proto": { "total": 0.001765373999660369, "count": 1, "is_parallel": true, "self": 0.0003526400005284813, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014127339991318877, "count": 8, "is_parallel": true, "self": 0.0014127339991318877 } } } } } } }, "UnityEnvironment.step": { "total": 1416.8311237509274, "count": 63912, "is_parallel": true, "self": 34.985161095874446, "children": { "UnityEnvironment._generate_step_input": { "total": 25.144624263142305, "count": 63912, "is_parallel": true, "self": 25.144624263142305 }, "communicator.exchange": { "total": 1254.666200946947, "count": 63912, "is_parallel": true, "self": 1254.666200946947 }, "steps_from_proto": { "total": 102.03513744496377, "count": 63912, "is_parallel": true, "self": 20.626056165771843, "children": { "_process_rank_one_or_two_observation": { "total": 81.40908127919192, "count": 511296, "is_parallel": true, "self": 81.40908127919192 } } } } } } } } } } }, "trainer_advance": { "total": 623.4447199319229, "count": 63913, "self": 2.7014012849940627, "children": { "process_trajectory": { "total": 129.11494960193113, "count": 63913, "self": 128.92141814193155, "children": { "RLTrainer._checkpoint": { "total": 0.19353145999957633, "count": 2, "self": 0.19353145999957633 } } }, "_update_policy": { "total": 491.6283690449977, "count": 450, "self": 290.99894024301284, "children": { "TorchPPOOptimizer.update": { "total": 200.6294288019849, "count": 22749, "self": 200.6294288019849 } } } } } } }, "trainer_threads": { "total": 1.2359996617306024e-06, "count": 1, "self": 1.2359996617306024e-06 }, "TrainerController._save_models": { "total": 0.08614171499993972, "count": 1, "self": 0.0014308230001915945, "children": { "RLTrainer._checkpoint": { "total": 0.08471089199974813, "count": 1, "self": 0.08471089199974813 } } } } } } }