{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407120943069458, "min": 1.407120943069458, "max": 1.425885796546936, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69825.5625, "min": 67969.3515625, "max": 77593.3984375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.98238747553816, "min": 89.14620938628158, "max": 400.864, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49558.0, "min": 48907.0, "max": 50204.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999957.0, "min": 49637.0, "max": 1999957.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999957.0, "min": 49637.0, "max": 1999957.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4539928436279297, "min": -0.02615596167743206, "max": 2.4547839164733887, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1253.9903564453125, "min": -3.2433393001556396, "max": 1358.768798828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8176695849097637, "min": 1.7548383224395014, "max": 3.8753163588371917, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1950.8291578888893, "min": 217.59995198249817, "max": 2143.978658914566, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8176695849097637, "min": 1.7548383224395014, "max": 3.8753163588371917, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1950.8291578888893, "min": 217.59995198249817, "max": 2143.978658914566, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01701510447860023, "min": 0.014531158714968722, "max": 0.01989825697770963, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05104531343580068, "min": 0.029062317429937444, "max": 0.05897078655931788, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06090267706248496, "min": 0.02275074003264308, "max": 0.06107522981862227, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18270803118745488, "min": 0.04550148006528616, "max": 0.18270803118745488, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3244488918833426e-06, "min": 3.3244488918833426e-06, "max": 0.0002953017015660999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.973346675650027e-06, "min": 9.973346675650027e-06, "max": 0.0008439873186708998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110811666666668, "min": 0.10110811666666668, "max": 0.1984339, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30332435, "min": 0.20734210000000003, "max": 0.5813291, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.529502166666684e-05, "min": 6.529502166666684e-05, "max": 0.00492185161, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001958850650000005, "min": 0.0001958850650000005, "max": 0.014068322090000003, "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": "1678103275", "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": "1.22.4", "end_time_seconds": "1678105740" }, "total": 2464.9769691829997, "count": 1, "self": 0.4468960909998714, "children": { "run_training.setup": { "total": 0.1062461629999234, "count": 1, "self": 0.1062461629999234 }, "TrainerController.start_learning": { "total": 2464.423826929, "count": 1, "self": 4.441555363046518, "children": { "TrainerController._reset_env": { "total": 10.134434693000003, "count": 1, "self": 10.134434693000003 }, "TrainerController.advance": { "total": 2449.737244558954, "count": 231695, "self": 4.57065297798863, "children": { "env_step": { "total": 1907.9283625969294, "count": 231695, "self": 1590.138868173967, "children": { "SubprocessEnvManager._take_step": { "total": 314.9301889940407, "count": 231695, "self": 16.753770968903837, "children": { "TorchPolicy.evaluate": { "total": 298.17641802513685, "count": 222978, "self": 74.91379138714387, "children": { "TorchPolicy.sample_actions": { "total": 223.26262663799298, "count": 222978, "self": 223.26262663799298 } } } } }, "workers": { "total": 2.8593054289217434, "count": 231695, "self": 0.0, "children": { "worker_root": { "total": 2456.074277887987, "count": 231695, "is_parallel": true, "self": 1167.039134227069, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009055419998276193, "count": 1, "is_parallel": true, "self": 0.0003450449999036209, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005604969999239984, "count": 2, "is_parallel": true, "self": 0.0005604969999239984 } } }, "UnityEnvironment.step": { "total": 0.030514734000007593, "count": 1, "is_parallel": true, "self": 0.0003039780003746273, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020430699987628032, "count": 1, "is_parallel": true, "self": 0.00020430699987628032 }, "communicator.exchange": { "total": 0.028518968999833305, "count": 1, "is_parallel": true, "self": 0.028518968999833305 }, "steps_from_proto": { "total": 0.00148747999992338, "count": 1, "is_parallel": true, "self": 0.0002790649998587469, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012084150000646332, "count": 2, "is_parallel": true, "self": 0.0012084150000646332 } } } } } } }, "UnityEnvironment.step": { "total": 1289.035143660918, "count": 231694, "is_parallel": true, "self": 38.77071092598612, "children": { "UnityEnvironment._generate_step_input": { "total": 83.05238640591892, "count": 231694, "is_parallel": true, "self": 83.05238640591892 }, "communicator.exchange": { "total": 1074.5152245019767, "count": 231694, "is_parallel": true, "self": 1074.5152245019767 }, "steps_from_proto": { "total": 92.69682182703627, "count": 231694, "is_parallel": true, "self": 39.69256609415493, "children": { "_process_rank_one_or_two_observation": { "total": 53.00425573288135, "count": 463388, "is_parallel": true, "self": 53.00425573288135 } } } } } } } } } } }, "trainer_advance": { "total": 537.2382289840361, "count": 231695, "self": 6.907044160983105, "children": { "process_trajectory": { "total": 167.8895153010501, "count": 231695, "self": 166.57349004104958, "children": { "RLTrainer._checkpoint": { "total": 1.3160252600005151, "count": 10, "self": 1.3160252600005151 } } }, "_update_policy": { "total": 362.44166952200294, "count": 97, "self": 304.3569444739983, "children": { "TorchPPOOptimizer.update": { "total": 58.08472504800466, "count": 2910, "self": 58.08472504800466 } } } } } } }, "trainer_threads": { "total": 1.183999756904086e-06, "count": 1, "self": 1.183999756904086e-06 }, "TrainerController._save_models": { "total": 0.11059112999964782, "count": 1, "self": 0.0019301959996482765, "children": { "RLTrainer._checkpoint": { "total": 0.10866093399999954, "count": 1, "self": 0.10866093399999954 } } } } } } }