{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4070676565170288, "min": 1.4070676565170288, "max": 1.4271095991134644, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70167.6484375, "min": 68881.5234375, "max": 77988.7578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 73.78176382660688, "min": 68.8, "max": 407.1138211382114, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49360.0, "min": 49192.0, "max": 50075.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999947.0, "min": 49591.0, "max": 1999947.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999947.0, "min": 49591.0, "max": 1999947.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.497603416442871, "min": 0.10721060633659363, "max": 2.5330913066864014, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1670.8966064453125, "min": 13.079693794250488, "max": 1779.790771484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9556491980816393, "min": 1.6629201177446569, "max": 4.023550900979107, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2646.329313516617, "min": 202.87625436484814, "max": 2800.476153612137, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9556491980816393, "min": 1.6629201177446569, "max": 4.023550900979107, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2646.329313516617, "min": 202.87625436484814, "max": 2800.476153612137, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016139968088161066, "min": 0.014142024184623854, "max": 0.0205603468800291, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0484199042644832, "min": 0.028284048369247708, "max": 0.05783989672878913, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05996234383847979, "min": 0.02053574404368798, "max": 0.05996234383847979, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17988703151543936, "min": 0.04107148808737596, "max": 0.17988703151543936, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.801148732983328e-06, "min": 3.801148732983328e-06, "max": 0.000295328926557025, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1403446198949983e-05, "min": 1.1403446198949983e-05, "max": 0.0008441832186055997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126701666666667, "min": 0.10126701666666667, "max": 0.19844297500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30380105, "min": 0.20766235000000005, "max": 0.5813943999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.322413166666657e-05, "min": 7.322413166666657e-05, "max": 0.0049223044525, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021967239499999972, "min": 0.00021967239499999972, "max": 0.014071580559999998, "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": "1718662516", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718664917" }, "total": 2401.469313765, "count": 1, "self": 0.4360581090004416, "children": { "run_training.setup": { "total": 0.05508938200000557, "count": 1, "self": 0.05508938200000557 }, "TrainerController.start_learning": { "total": 2400.9781662739997, "count": 1, "self": 4.274294453986386, "children": { "TrainerController._reset_env": { "total": 3.6932327259999624, "count": 1, "self": 3.6932327259999624 }, "TrainerController.advance": { "total": 2392.8979110770133, "count": 233000, "self": 4.691333084108919, "children": { "env_step": { "total": 1886.9034306298906, "count": 233000, "self": 1553.561546576932, "children": { "SubprocessEnvManager._take_step": { "total": 330.42070033691584, "count": 233000, "self": 17.710169874887583, "children": { "TorchPolicy.evaluate": { "total": 312.71053046202826, "count": 222882, "self": 312.71053046202826 } } }, "workers": { "total": 2.9211837160427763, "count": 233000, "self": 0.0, "children": { "worker_root": { "total": 2393.762643227013, "count": 233000, "is_parallel": true, "self": 1143.139958284047, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009859689999984766, "count": 1, "is_parallel": true, "self": 0.00025558000004366477, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007303889999548119, "count": 2, "is_parallel": true, "self": 0.0007303889999548119 } } }, "UnityEnvironment.step": { "total": 0.028627153999991606, "count": 1, "is_parallel": true, "self": 0.00037173899994513704, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020355300000574061, "count": 1, "is_parallel": true, "self": 0.00020355300000574061 }, "communicator.exchange": { "total": 0.027324510000028113, "count": 1, "is_parallel": true, "self": 0.027324510000028113 }, "steps_from_proto": { "total": 0.0007273520000126155, "count": 1, "is_parallel": true, "self": 0.00018991900003584306, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005374329999767724, "count": 2, "is_parallel": true, "self": 0.0005374329999767724 } } } } } } }, "UnityEnvironment.step": { "total": 1250.622684942966, "count": 232999, "is_parallel": true, "self": 39.32257484285378, "children": { "UnityEnvironment._generate_step_input": { "total": 80.2379226680153, "count": 232999, "is_parallel": true, "self": 80.2379226680153 }, "communicator.exchange": { "total": 1042.033701737013, "count": 232999, "is_parallel": true, "self": 1042.033701737013 }, "steps_from_proto": { "total": 89.0284856950841, "count": 232999, "is_parallel": true, "self": 31.70603953497283, "children": { "_process_rank_one_or_two_observation": { "total": 57.32244616011127, "count": 465998, "is_parallel": true, "self": 57.32244616011127 } } } } } } } } } } }, "trainer_advance": { "total": 501.3031473630139, "count": 233000, "self": 6.554250816993942, "children": { "process_trajectory": { "total": 161.53352382001987, "count": 233000, "self": 160.2352437600196, "children": { "RLTrainer._checkpoint": { "total": 1.298280060000252, "count": 10, "self": 1.298280060000252 } } }, "_update_policy": { "total": 333.2153727260001, "count": 97, "self": 267.9231838110028, "children": { "TorchPPOOptimizer.update": { "total": 65.29218891499733, "count": 2910, "self": 65.29218891499733 } } } } } } }, "trainer_threads": { "total": 1.1610000001383014e-06, "count": 1, "self": 1.1610000001383014e-06 }, "TrainerController._save_models": { "total": 0.11272685599988108, "count": 1, "self": 0.0018450799998390721, "children": { "RLTrainer._checkpoint": { "total": 0.11088177600004201, "count": 1, "self": 0.11088177600004201 } } } } } } }