| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.543377161026001, |
| "min": 0.543377161026001, |
| "max": 1.5370537042617798, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 16605.60546875, |
| "min": 16605.60546875, |
| "max": 49185.71875, |
| "count": 30 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 899962.0, |
| "min": 29889.0, |
| "max": 899962.0, |
| "count": 30 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 899962.0, |
| "min": 29889.0, |
| "max": 899962.0, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.47721928358078003, |
| "min": -0.08921089768409729, |
| "max": 0.47807711362838745, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 71.10567474365234, |
| "min": -10.79451847076416, |
| "max": 71.23348999023438, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.01822402887046337, |
| "min": 0.01822402887046337, |
| "max": 0.4311797022819519, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.7153801918029785, |
| "min": 2.7153801918029785, |
| "max": 51.7415657043457, |
| "count": 30 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07097543162864217, |
| "min": 0.0662510189934116, |
| "max": 0.07539826402190011, |
| "count": 30 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.4968280214004952, |
| "min": 0.30159305608760045, |
| "max": 0.5675650316686252, |
| "count": 30 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014882371662747603, |
| "min": 0.00047812975080548705, |
| "max": 0.016555759260632682, |
| "count": 30 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.10417660163923323, |
| "min": 0.0033469082556384093, |
| "max": 0.11589031482442878, |
| "count": 30 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 4.952288825460318e-06, |
| "min": 4.952288825460318e-06, |
| "max": 0.00029359325213558333, |
| "count": 30 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 3.466602177822223e-05, |
| "min": 3.466602177822223e-05, |
| "max": 0.0017846834384388883, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10165073015873016, |
| "min": 0.10165073015873016, |
| "max": 0.19786441666666668, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 0.7115551111111111, |
| "min": 0.7115551111111111, |
| "max": 1.2948944444444446, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00017490794285714294, |
| "min": 0.00017490794285714294, |
| "max": 0.009786655225, |
| "count": 30 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0012243556000000005, |
| "min": 0.0012243556000000005, |
| "max": 0.059499955, |
| "count": 30 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.024776523932814598, |
| "min": 0.024776523932814598, |
| "max": 0.5557849407196045, |
| "count": 30 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.17343567311763763, |
| "min": 0.17343567311763763, |
| "max": 2.223139762878418, |
| "count": 30 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 414.6619718309859, |
| "min": 384.8961038961039, |
| "max": 998.28125, |
| "count": 30 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29441.0, |
| "min": 17105.0, |
| "max": 32722.0, |
| "count": 30 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.4162788475063486, |
| "min": -0.9318303592277296, |
| "max": 1.5635640789300969, |
| "count": 30 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 100.55579817295074, |
| "min": -30.750401854515076, |
| "max": 121.95799815654755, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.4162788475063486, |
| "min": -0.9318303592277296, |
| "max": 1.5635640789300969, |
| "count": 30 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 100.55579817295074, |
| "min": -30.750401854515076, |
| "max": 121.95799815654755, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.10599076124334472, |
| "min": 0.10599076124334472, |
| "max": 14.495310430941375, |
| "count": 30 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 7.525344048277475, |
| "min": 7.525344048277475, |
| "max": 333.3921399116516, |
| "count": 30 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 30 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 30 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1673962258", |
| "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
| "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": "0.29.0.dev0", |
| "mlagents_envs_version": "0.29.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.8.1+cu102", |
| "numpy_version": "1.21.6", |
| "end_time_seconds": "1673964097" |
| }, |
| "total": 1838.3410817459999, |
| "count": 1, |
| "self": 0.44730051699957585, |
| "children": { |
| "run_training.setup": { |
| "total": 0.11338297300000022, |
| "count": 1, |
| "self": 0.11338297300000022 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1837.7803982560004, |
| "count": 1, |
| "self": 1.044448762962702, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 9.878776490000007, |
| "count": 1, |
| "self": 9.878776490000007 |
| }, |
| "TrainerController.advance": { |
| "total": 1826.7176801400374, |
| "count": 57328, |
| "self": 1.0790583550256088, |
| "children": { |
| "env_step": { |
| "total": 1215.15605292102, |
| "count": 57328, |
| "self": 1119.7055291790293, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 94.80150577700198, |
| "count": 57328, |
| "self": 3.7677913459835963, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 91.03371443101838, |
| "count": 56388, |
| "self": 29.231409146012936, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 61.802305285005446, |
| "count": 56388, |
| "self": 61.802305285005446 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.6490179649887295, |
| "count": 57328, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1834.6925994309595, |
| "count": 57328, |
| "is_parallel": true, |
| "self": 799.7106329099897, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.006327580000004218, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00376651099998071, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002561069000023508, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002561069000023508 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04645403299997497, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005296890000749954, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00047250399995846237, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00047250399995846237 |
| }, |
| "communicator.exchange": { |
| "total": 0.04377851699996427, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04377851699996427 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016733229999772448, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004165209999769104, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012568020000003344, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012568020000003344 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1034.9819665209698, |
| "count": 57327, |
| "is_parallel": true, |
| "self": 24.96411753502366, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 20.158003167994764, |
| "count": 57327, |
| "is_parallel": true, |
| "self": 20.158003167994764 |
| }, |
| "communicator.exchange": { |
| "total": 907.7361858519679, |
| "count": 57327, |
| "is_parallel": true, |
| "self": 907.7361858519679 |
| }, |
| "steps_from_proto": { |
| "total": 82.1236599659835, |
| "count": 57327, |
| "is_parallel": true, |
| "self": 18.978752959899907, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 63.1449070060836, |
| "count": 458616, |
| "is_parallel": true, |
| "self": 63.1449070060836 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 610.4825688639917, |
| "count": 57328, |
| "self": 2.13188788997968, |
| "children": { |
| "process_trajectory": { |
| "total": 119.3457562240128, |
| "count": 57328, |
| "self": 119.2098123620126, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1359438620002038, |
| "count": 1, |
| "self": 0.1359438620002038 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 489.00492474999913, |
| "count": 204, |
| "self": 183.1068267150187, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 305.8980980349804, |
| "count": 20730, |
| "self": 305.8980980349804 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.619999789516442e-07, |
| "count": 1, |
| "self": 8.619999789516442e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.13949200100023518, |
| "count": 1, |
| "self": 0.002155748999939533, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.13733625200029564, |
| "count": 1, |
| "self": 0.13733625200029564 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
