{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4100078344345093, "min": 1.4100078344345093, "max": 1.4281668663024902, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72711.28125, "min": 68666.2734375, "max": 77227.140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.3875236294896, "min": 83.39797639123103, "max": 389.8759689922481, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49402.0, "min": 48794.0, "max": 50294.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999966.0, "min": 49919.0, "max": 1999966.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999966.0, "min": 49919.0, "max": 1999966.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4214024543762207, "min": 0.103665292263031, "max": 2.4332103729248047, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1280.921875, "min": 13.269157409667969, "max": 1416.687744140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.803950002040214, "min": 1.822086970321834, "max": 3.8830046844652113, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2012.2895510792732, "min": 233.22713220119476, "max": 2207.6898906230927, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.803950002040214, "min": 1.822086970321834, "max": 3.8830046844652113, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2012.2895510792732, "min": 233.22713220119476, "max": 2207.6898906230927, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015709180133287898, "min": 0.013760402636641326, "max": 0.02076351023085105, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04712754039986369, "min": 0.027520805273282652, "max": 0.05749262075114529, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05156955739690198, "min": 0.021725681237876417, "max": 0.06184928417205811, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15470867219070594, "min": 0.04345136247575283, "max": 0.17795845145980516, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6394987868666702e-06, "min": 3.6394987868666702e-06, "max": 0.0002952888015704, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0918496360600011e-05, "min": 1.0918496360600011e-05, "max": 0.0008438031187322998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121313333333336, "min": 0.10121313333333336, "max": 0.19842960000000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30363940000000006, "min": 0.20756314999999997, "max": 0.5812676999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.05353533333334e-05, "min": 7.05353533333334e-05, "max": 0.004921637039999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002116060600000002, "min": 0.0002116060600000002, "max": 0.014065258229999999, "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": "1687436451", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1687439039" }, "total": 2587.4395724449996, "count": 1, "self": 0.43047647399998823, "children": { "run_training.setup": { "total": 0.04460062799989828, "count": 1, "self": 0.04460062799989828 }, "TrainerController.start_learning": { "total": 2586.9644953429997, "count": 1, "self": 4.69158299204264, "children": { "TrainerController._reset_env": { "total": 4.4180825770001775, "count": 1, "self": 4.4180825770001775 }, "TrainerController.advance": { "total": 2577.7327168629567, "count": 232266, "self": 4.884294396007135, "children": { "env_step": { "total": 2033.2793595470273, "count": 232266, "self": 1713.2934258989455, "children": { "SubprocessEnvManager._take_step": { "total": 316.91854450707524, "count": 232266, "self": 18.669691429018485, "children": { "TorchPolicy.evaluate": { "total": 298.24885307805675, "count": 223030, "self": 298.24885307805675 } } }, "workers": { "total": 3.0673891410065153, "count": 232266, "self": 0.0, "children": { "worker_root": { "total": 2578.572771342011, "count": 232266, "is_parallel": true, "self": 1180.5070152130563, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010458399999606627, "count": 1, "is_parallel": true, "self": 0.00030352399994626467, "children": { "_process_rank_one_or_two_observation": { "total": 0.000742316000014398, "count": 2, "is_parallel": true, "self": 0.000742316000014398 } } }, "UnityEnvironment.step": { "total": 0.08208223399992676, "count": 1, "is_parallel": true, "self": 0.00034653599982448213, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021578099995167577, "count": 1, "is_parallel": true, "self": 0.00021578099995167577 }, "communicator.exchange": { "total": 0.08071256400012317, "count": 1, "is_parallel": true, "self": 0.08071256400012317 }, "steps_from_proto": { "total": 0.0008073530000274332, "count": 1, "is_parallel": true, "self": 0.0002642130000367615, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005431399999906716, "count": 2, "is_parallel": true, "self": 0.0005431399999906716 } } } } } } }, "UnityEnvironment.step": { "total": 1398.0657561289547, "count": 232265, "is_parallel": true, "self": 41.49447925674713, "children": { "UnityEnvironment._generate_step_input": { "total": 88.2621931250817, "count": 232265, "is_parallel": true, "self": 88.2621931250817 }, "communicator.exchange": { "total": 1166.4627097830496, "count": 232265, "is_parallel": true, "self": 1166.4627097830496 }, "steps_from_proto": { "total": 101.84637396407629, "count": 232265, "is_parallel": true, "self": 39.01303891104021, "children": { "_process_rank_one_or_two_observation": { "total": 62.83333505303608, "count": 464530, "is_parallel": true, "self": 62.83333505303608 } } } } } } } } } } }, "trainer_advance": { "total": 539.5690629199223, "count": 232266, "self": 7.174684963963273, "children": { "process_trajectory": { "total": 145.37987289195735, "count": 232266, "self": 144.01666686695762, "children": { "RLTrainer._checkpoint": { "total": 1.3632060249997267, "count": 10, "self": 1.3632060249997267 } } }, "_update_policy": { "total": 387.0145050640017, "count": 97, "self": 326.1828505310018, "children": { "TorchPPOOptimizer.update": { "total": 60.83165453299989, "count": 2910, "self": 60.83165453299989 } } } } } } }, "trainer_threads": { "total": 1.1669999366858974e-06, "count": 1, "self": 1.1669999366858974e-06 }, "TrainerController._save_models": { "total": 0.12211174399999436, "count": 1, "self": 0.0026257839999743737, "children": { "RLTrainer._checkpoint": { "total": 0.11948596000001999, "count": 1, "self": 0.11948596000001999 } } } } } } }