{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4146970510482788, "min": 1.4146970510482788, "max": 1.4337280988693237, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70712.21875, "min": 68788.875, "max": 77510.96875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.7053726169844, "min": 80.9672131147541, "max": 394.12598425196853, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49452.0, "min": 48823.0, "max": 50054.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999945.0, "min": 49541.0, "max": 1999945.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999945.0, "min": 49541.0, "max": 1999945.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.46536922454834, "min": 0.06362206488847733, "max": 2.5356128215789795, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1422.51806640625, "min": 8.016380310058594, "max": 1485.1201171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7921058387855515, "min": 1.755386782070947, "max": 3.9195486399362673, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2188.0450689792633, "min": 221.17873454093933, "max": 2306.433808386326, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7921058387855515, "min": 1.755386782070947, "max": 3.9195486399362673, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2188.0450689792633, "min": 221.17873454093933, "max": 2306.433808386326, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015708528018472456, "min": 0.011685455027327409, "max": 0.01936083516193321, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04712558405541737, "min": 0.023370910054654817, "max": 0.05520253065624274, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06073739615579447, "min": 0.02123288316652179, "max": 0.06073739615579447, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1822121884673834, "min": 0.04246576633304358, "max": 0.1822121884673834, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3390988869999926e-06, "min": 3.3390988869999926e-06, "max": 0.000295301776566075, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0017296660999977e-05, "min": 1.0017296660999977e-05, "max": 0.00084398146867285, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111300000000002, "min": 0.10111300000000002, "max": 0.19843392500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033390000000001, "min": 0.20735430000000005, "max": 0.5813271500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.553869999999988e-05, "min": 6.553869999999988e-05, "max": 0.0049218528575, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019661609999999964, "min": 0.00019661609999999964, "max": 0.014068224785, "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": "1699600518", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699602874" }, "total": 2355.475442479, "count": 1, "self": 0.438622822999605, "children": { "run_training.setup": { "total": 0.04354286699998511, "count": 1, "self": 0.04354286699998511 }, "TrainerController.start_learning": { "total": 2354.9932767890004, "count": 1, "self": 4.277120074882532, "children": { "TrainerController._reset_env": { "total": 8.864668692999999, "count": 1, "self": 8.864668692999999 }, "TrainerController.advance": { "total": 2341.771536765118, "count": 232522, "self": 4.369145641105661, "children": { "env_step": { "total": 1851.9791973440156, "count": 232522, "self": 1523.5019000911248, "children": { "SubprocessEnvManager._take_step": { "total": 325.7346683969346, "count": 232522, "self": 15.94908196691648, "children": { "TorchPolicy.evaluate": { "total": 309.7855864300181, "count": 222942, "self": 309.7855864300181 } } }, "workers": { "total": 2.742628855956127, "count": 232522, "self": 0.0, "children": { "worker_root": { "total": 2347.852569213002, "count": 232522, "is_parallel": true, "self": 1103.8264920929632, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008135730000162766, "count": 1, "is_parallel": true, "self": 0.00021936000001687717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005942129999993995, "count": 2, "is_parallel": true, "self": 0.0005942129999993995 } } }, "UnityEnvironment.step": { "total": 0.03021798000003173, "count": 1, "is_parallel": true, "self": 0.00028750900003160496, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001995769999894037, "count": 1, "is_parallel": true, "self": 0.0001995769999894037 }, "communicator.exchange": { "total": 0.028999458000043887, "count": 1, "is_parallel": true, "self": 0.028999458000043887 }, "steps_from_proto": { "total": 0.0007314359999668341, "count": 1, "is_parallel": true, "self": 0.00020384699996611744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005275890000007166, "count": 2, "is_parallel": true, "self": 0.0005275890000007166 } } } } } } }, "UnityEnvironment.step": { "total": 1244.0260771200387, "count": 232521, "is_parallel": true, "self": 39.606857569088106, "children": { "UnityEnvironment._generate_step_input": { "total": 81.07868312301309, "count": 232521, "is_parallel": true, "self": 81.07868312301309 }, "communicator.exchange": { "total": 1035.5976016220156, "count": 232521, "is_parallel": true, "self": 1035.5976016220156 }, "steps_from_proto": { "total": 87.742934805922, "count": 232521, "is_parallel": true, "self": 30.80788495491538, "children": { "_process_rank_one_or_two_observation": { "total": 56.935049851006625, "count": 465042, "is_parallel": true, "self": 56.935049851006625 } } } } } } } } } } }, "trainer_advance": { "total": 485.4231937799969, "count": 232522, "self": 6.2356267869689646, "children": { "process_trajectory": { "total": 150.9366360020278, "count": 232522, "self": 149.9951431360269, "children": { "RLTrainer._checkpoint": { "total": 0.9414928660008854, "count": 10, "self": 0.9414928660008854 } } }, "_update_policy": { "total": 328.25093099100013, "count": 97, "self": 273.56675956598997, "children": { "TorchPPOOptimizer.update": { "total": 54.68417142501016, "count": 2910, "self": 54.68417142501016 } } } } } } }, "trainer_threads": { "total": 1.1199999789823778e-06, "count": 1, "self": 1.1199999789823778e-06 }, "TrainerController._save_models": { "total": 0.07995013599975209, "count": 1, "self": 0.000997371999801544, "children": { "RLTrainer._checkpoint": { "total": 0.07895276399995055, "count": 1, "self": 0.07895276399995055 } } } } } } }