{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44912347197532654, "min": 0.44829437136650085, "max": 1.459127426147461, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13358.728515625, "min": 13358.728515625, "max": 44264.08984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.32942643761634827, "min": -0.12526600062847137, "max": 0.3584676682949066, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 84.66259765625, "min": -30.18910789489746, "max": 92.84312438964844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004904638044536114, "min": 0.00212547997944057, "max": 0.22454407811164856, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.260491967201233, "min": 0.5377464294433594, "max": 54.1151237487793, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06985345459681759, "min": 0.0657316405434228, "max": 0.07379627501598648, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9779483643554462, "min": 0.49256165636651184, "max": 1.0397710791245722, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011089424375920013, "min": 0.0004076620917615216, "max": 0.012793812375180314, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15525194126288017, "min": 0.005299607192899781, "max": 0.17911337325252438, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.597104610521427e-06, "min": 7.597104610521427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010635946454729998, "min": 0.00010635946454729998, "max": 0.0032561567146144996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253233571428573, "min": 0.10253233571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354527000000001, "min": 1.3886848, "max": 2.3853855000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002629803378571429, "min": 0.0002629803378571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00368172473, "min": 0.00368172473, "max": 0.10856001145000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01090999972075224, "min": 0.010771428234875202, "max": 0.43669724464416504, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1527400016784668, "min": 0.15079998970031738, "max": 3.0568807125091553, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 518.578947368421, "min": 490.78333333333336, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29559.0, "min": 15984.0, "max": 32223.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1304210241426502, "min": -1.0000000521540642, "max": 1.2424666322767735, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.43399837613106, "min": -29.96380166709423, "max": 74.54799793660641, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1304210241426502, "min": -1.0000000521540642, "max": 1.2424666322767735, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.43399837613106, "min": -29.96380166709423, "max": 74.54799793660641, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0587151825526043, "min": 0.054262425736912215, "max": 8.471816313453019, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.346765405498445, "min": 3.255745544214733, "max": 135.5490610152483, "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": "1787659350", "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": "1787661855" }, "total": 2505.5211165539995, "count": 1, "self": 0.5296329679995324, "children": { "run_training.setup": { "total": 0.02452394700003424, "count": 1, "self": 0.02452394700003424 }, "TrainerController.start_learning": { "total": 2504.966959639, "count": 1, "self": 1.6317040978974546, "children": { "TrainerController._reset_env": { "total": 2.1734966310000345, "count": 1, "self": 2.1734966310000345 }, "TrainerController.advance": { "total": 2501.0694717901015, "count": 63380, "self": 1.5876212550460878, "children": { "env_step": { "total": 1828.9176462840078, "count": 63380, "self": 1656.505584552021, "children": { "SubprocessEnvManager._take_step": { "total": 171.47006853800804, "count": 63380, "self": 5.202593275959316, "children": { "TorchPolicy.evaluate": { "total": 166.26747526204872, "count": 62564, "self": 166.26747526204872 } } }, "workers": { "total": 0.9419931939787602, "count": 63380, "self": 0.0, "children": { "worker_root": { "total": 2498.869685851089, "count": 63380, "is_parallel": true, "self": 975.2516152960975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018159820001528715, "count": 1, "is_parallel": true, "self": 0.0005663460001414933, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012496360000113782, "count": 8, "is_parallel": true, "self": 0.0012496360000113782 } } }, "UnityEnvironment.step": { "total": 0.0623888749996695, "count": 1, "is_parallel": true, "self": 0.0005418359992290789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005267400001685019, "count": 1, "is_parallel": true, "self": 0.0005267400001685019 }, "communicator.exchange": { "total": 0.05959522500006642, "count": 1, "is_parallel": true, "self": 0.05959522500006642 }, "steps_from_proto": { "total": 0.0017250740002054954, "count": 1, "is_parallel": true, "self": 0.00038487099982376094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013402030003817345, "count": 8, "is_parallel": true, "self": 0.0013402030003817345 } } } } } } }, "UnityEnvironment.step": { "total": 1523.6180705549914, "count": 63379, "is_parallel": true, "self": 37.62466095101718, "children": { "UnityEnvironment._generate_step_input": { "total": 26.640666370962208, "count": 63379, "is_parallel": true, "self": 26.640666370962208 }, "communicator.exchange": { "total": 1334.8779385270013, "count": 63379, "is_parallel": true, "self": 1334.8779385270013 }, "steps_from_proto": { "total": 124.47480470601067, "count": 63379, "is_parallel": true, "self": 25.655858211909617, "children": { "_process_rank_one_or_two_observation": { "total": 98.81894649410106, "count": 507032, "is_parallel": true, "self": 98.81894649410106 } } } } } } } } } } }, "trainer_advance": { "total": 670.5642042510476, "count": 63380, "self": 2.7705597691669936, "children": { "process_trajectory": { "total": 116.74718594687738, "count": 63380, "self": 116.52374694987702, "children": { "RLTrainer._checkpoint": { "total": 0.22343899700035763, "count": 2, "self": 0.22343899700035763 } } }, "_update_policy": { "total": 551.0464585350032, "count": 442, "self": 294.9093710510001, "children": { "TorchPPOOptimizer.update": { "total": 256.13708748400313, "count": 22800, "self": 256.13708748400313 } } } } } } }, "trainer_threads": { "total": 1.0550002116360702e-06, "count": 1, "self": 1.0550002116360702e-06 }, "TrainerController._save_models": { "total": 0.0922860650007351, "count": 1, "self": 0.001150422001046536, "children": { "RLTrainer._checkpoint": { "total": 0.09113564299968857, "count": 1, "self": 0.09113564299968857 } } } } } } }