{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404396414756775, "min": 1.404396414756775, "max": 1.4258482456207275, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69486.7265625, "min": 67715.8203125, "max": 77362.7421875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 122.55061728395061, "min": 94.47227533460803, "max": 409.38524590163934, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49633.0, "min": 48868.0, "max": 50250.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999986.0, "min": 49641.0, "max": 1999986.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999986.0, "min": 49641.0, "max": 1999986.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3241357803344727, "min": 0.08291309326887131, "max": 2.402446985244751, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 941.2750244140625, "min": 10.03248405456543, "max": 1227.0843505859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5403750512335037, "min": 1.9657032477461602, "max": 3.922117276649999, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1433.851895749569, "min": 237.85009297728539, "max": 1917.4316394925117, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5403750512335037, "min": 1.9657032477461602, "max": 3.922117276649999, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1433.851895749569, "min": 237.85009297728539, "max": 1917.4316394925117, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017841476676039747, "min": 0.013698274325967456, "max": 0.020117781956731858, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.035682953352079494, "min": 0.027396548651934912, "max": 0.06035334587019557, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04422835173706213, "min": 0.023145649085442227, "max": 0.057467390907307465, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08845670347412427, "min": 0.046291298170884454, "max": 0.1674029848227898, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.477898507399998e-06, "min": 4.477898507399998e-06, "max": 0.0002953740765419749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.955797014799997e-06, "min": 8.955797014799997e-06, "max": 0.0008443794185401999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1014926, "min": 0.1014926, "max": 0.19845802499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2029852, "min": 0.2029852, "max": 0.5814598000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.448073999999997e-05, "min": 8.448073999999997e-05, "max": 0.004923055447500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016896147999999995, "min": 0.00016896147999999995, "max": 0.01407484402, "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": "1675189350", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.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": "1675191584" }, "total": 2234.365482131, "count": 1, "self": 0.39587949600036154, "children": { "run_training.setup": { "total": 0.10249701999998706, "count": 1, "self": 0.10249701999998706 }, "TrainerController.start_learning": { "total": 2233.8671056149997, "count": 1, "self": 4.068433431102221, "children": { "TrainerController._reset_env": { "total": 10.343042406999984, "count": 1, "self": 10.343042406999984 }, "TrainerController.advance": { "total": 2219.350670593897, "count": 231213, "self": 4.283122819774235, "children": { "env_step": { "total": 1767.0473897910324, "count": 231213, "self": 1482.2508546340612, "children": { "SubprocessEnvManager._take_step": { "total": 282.23454217298234, "count": 231213, "self": 14.782793667925944, "children": { "TorchPolicy.evaluate": { "total": 267.4517485050564, "count": 222960, "self": 66.31291305304, "children": { "TorchPolicy.sample_actions": { "total": 201.1388354520164, "count": 222960, "self": 201.1388354520164 } } } } }, "workers": { "total": 2.5619929839889437, "count": 231213, "self": 0.0, "children": { "worker_root": { "total": 2225.9079090720484, "count": 231213, "is_parallel": true, "self": 1008.9452911860994, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016925959999980478, "count": 1, "is_parallel": true, "self": 0.0003191680000327324, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013734279999653154, "count": 2, "is_parallel": true, "self": 0.0013734279999653154 } } }, "UnityEnvironment.step": { "total": 0.029897363999964455, "count": 1, "is_parallel": true, "self": 0.00027049999994233076, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020496199999797682, "count": 1, "is_parallel": true, "self": 0.00020496199999797682 }, "communicator.exchange": { "total": 0.028550626000026114, "count": 1, "is_parallel": true, "self": 0.028550626000026114 }, "steps_from_proto": { "total": 0.0008712759999980335, "count": 1, "is_parallel": true, "self": 0.0003975390000050538, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004737369999929797, "count": 2, "is_parallel": true, "self": 0.0004737369999929797 } } } } } } }, "UnityEnvironment.step": { "total": 1216.962617885949, "count": 231212, "is_parallel": true, "self": 34.09105130879925, "children": { "UnityEnvironment._generate_step_input": { "total": 79.85015904206352, "count": 231212, "is_parallel": true, "self": 79.85015904206352 }, "communicator.exchange": { "total": 1009.7330422309941, "count": 231212, "is_parallel": true, "self": 1009.7330422309941 }, "steps_from_proto": { "total": 93.28836530409222, "count": 231212, "is_parallel": true, "self": 40.649436895204474, "children": { "_process_rank_one_or_two_observation": { "total": 52.63892840888775, "count": 462424, "is_parallel": true, "self": 52.63892840888775 } } } } } } } } } } }, "trainer_advance": { "total": 448.02015798309054, "count": 231213, "self": 6.501406786093185, "children": { "process_trajectory": { "total": 140.71479882599652, "count": 231213, "self": 139.62860828399624, "children": { "RLTrainer._checkpoint": { "total": 1.0861905420002813, "count": 10, "self": 1.0861905420002813 } } }, "_update_policy": { "total": 300.80395237100083, "count": 96, "self": 248.61343861000222, "children": { "TorchPPOOptimizer.update": { "total": 52.19051376099861, "count": 2880, "self": 52.19051376099861 } } } } } } }, "trainer_threads": { "total": 9.870000212686136e-07, "count": 1, "self": 9.870000212686136e-07 }, "TrainerController._save_models": { "total": 0.10495819600009781, "count": 1, "self": 0.002614564999930735, "children": { "RLTrainer._checkpoint": { "total": 0.10234363100016708, "count": 1, "self": 0.10234363100016708 } } } } } } }