{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4070724248886108, "min": 1.4070724248886108, "max": 1.4291751384735107, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70255.125, "min": 67283.3359375, "max": 79915.546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 106.95680345572354, "min": 82.19134775374376, "max": 424.0, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49521.0, "min": 49165.0, "max": 50120.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999973.0, "min": 49432.0, "max": 1999973.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999973.0, "min": 49432.0, "max": 1999973.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.315603494644165, "min": 0.06453980505466461, "max": 2.4812848567962646, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1072.1243896484375, "min": 7.551156997680664, "max": 1458.157958984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.421364369969131, "min": 2.0234359235335617, "max": 3.9674112116437583, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1584.0917032957077, "min": 236.74200305342674, "max": 2384.414138197899, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.421364369969131, "min": 2.0234359235335617, "max": 3.9674112116437583, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1584.0917032957077, "min": 236.74200305342674, "max": 2384.414138197899, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018010613367530622, "min": 0.011901670469122414, "max": 0.020557434094371274, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05403184010259186, "min": 0.02380334093824483, "max": 0.059350711955145616, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.048276150516337824, "min": 0.021620574469367663, "max": 0.06343948977688948, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14482845154901347, "min": 0.043241148938735326, "max": 0.17967674769461156, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1028489657500085e-06, "min": 3.1028489657500085e-06, "max": 0.000295274476575175, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.308546897250026e-06, "min": 9.308546897250026e-06, "max": 0.0008437017187660998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10103425000000003, "min": 0.10103425000000003, "max": 0.19842482500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031027500000001, "min": 0.20724945, "max": 0.5812339000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.160907500000017e-05, "min": 6.160907500000017e-05, "max": 0.0049213987675, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018482722500000052, "min": 0.00018482722500000052, "max": 0.01406357161, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694196803", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1694199319" }, "total": 2515.441576524, "count": 1, "self": 0.39167299600012484, "children": { "run_training.setup": { "total": 0.06301339400010875, "count": 1, "self": 0.06301339400010875 }, "TrainerController.start_learning": { "total": 2514.9868901339996, "count": 1, "self": 4.545852993052904, "children": { "TrainerController._reset_env": { "total": 4.915808806000086, "count": 1, "self": 4.915808806000086 }, "TrainerController.advance": { "total": 2505.404180748947, "count": 232419, "self": 4.7343023882122, "children": { "env_step": { "total": 1946.8714471907979, "count": 232419, "self": 1644.30081255692, "children": { "SubprocessEnvManager._take_step": { "total": 299.560436999953, "count": 232419, "self": 17.16815577692796, "children": { "TorchPolicy.evaluate": { "total": 282.39228122302507, "count": 223080, "self": 282.39228122302507 } } }, "workers": { "total": 3.0101976339249177, "count": 232419, "self": 0.0, "children": { "worker_root": { "total": 2507.3594481460536, "count": 232419, "is_parallel": true, "self": 1164.4183402570711, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010965120000037132, "count": 1, "is_parallel": true, "self": 0.00032571800011282903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007707939998908842, "count": 2, "is_parallel": true, "self": 0.0007707939998908842 } } }, "UnityEnvironment.step": { "total": 0.03204788300013206, "count": 1, "is_parallel": true, "self": 0.0003527460000896099, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002422600000500097, "count": 1, "is_parallel": true, "self": 0.0002422600000500097 }, "communicator.exchange": { "total": 0.030677745000048162, "count": 1, "is_parallel": true, "self": 0.030677745000048162 }, "steps_from_proto": { "total": 0.0007751319999442785, "count": 1, "is_parallel": true, "self": 0.000225006999926336, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005501250000179425, "count": 2, "is_parallel": true, "self": 0.0005501250000179425 } } } } } } }, "UnityEnvironment.step": { "total": 1342.9411078889825, "count": 232418, "is_parallel": true, "self": 40.2749665729591, "children": { "UnityEnvironment._generate_step_input": { "total": 86.32293315411084, "count": 232418, "is_parallel": true, "self": 86.32293315411084 }, "communicator.exchange": { "total": 1114.7033896609496, "count": 232418, "is_parallel": true, "self": 1114.7033896609496 }, "steps_from_proto": { "total": 101.63981850096297, "count": 232418, "is_parallel": true, "self": 38.762589105116604, "children": { "_process_rank_one_or_two_observation": { "total": 62.87722939584637, "count": 464836, "is_parallel": true, "self": 62.87722939584637 } } } } } } } } } } }, "trainer_advance": { "total": 553.798431169937, "count": 232419, "self": 6.479552475758737, "children": { "process_trajectory": { "total": 142.23268056517782, "count": 232419, "self": 140.64142143917752, "children": { "RLTrainer._checkpoint": { "total": 1.5912591260002955, "count": 10, "self": 1.5912591260002955 } } }, "_update_policy": { "total": 405.0861981290004, "count": 97, "self": 345.43451777500127, "children": { "TorchPPOOptimizer.update": { "total": 59.651680353999154, "count": 2910, "self": 59.651680353999154 } } } } } } }, "trainer_threads": { "total": 1.165999947261298e-06, "count": 1, "self": 1.165999947261298e-06 }, "TrainerController._save_models": { "total": 0.12104641999985688, "count": 1, "self": 0.0024513489997843863, "children": { "RLTrainer._checkpoint": { "total": 0.1185950710000725, "count": 1, "self": 0.1185950710000725 } } } } } } }