{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4092086553573608, "min": 1.4092086553573608, "max": 1.4273231029510498, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70949.4296875, "min": 68785.1953125, "max": 77344.046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.53507340946166, "min": 77.5, "max": 375.9924812030075, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49368.0, "min": 48821.0, "max": 50029.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999981.0, "min": 49937.0, "max": 1999981.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999981.0, "min": 49937.0, "max": 1999981.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4379827976226807, "min": 0.1499248445034027, "max": 2.5412046909332275, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1494.4833984375, "min": 19.79007911682129, "max": 1534.07568359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.799930379402385, "min": 1.785288857916991, "max": 4.018157347744586, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2329.357322573662, "min": 235.6581292450428, "max": 2360.3017317056656, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.799930379402385, "min": 1.785288857916991, "max": 4.018157347744586, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2329.357322573662, "min": 235.6581292450428, "max": 2360.3017317056656, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014388886248020247, "min": 0.013140877066568161, "max": 0.020331538838217963, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04316665874406074, "min": 0.026281754133136322, "max": 0.05784384801130121, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05418469868600368, "min": 0.022841385224213202, "max": 0.06374579357604186, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16255409605801105, "min": 0.045682770448426405, "max": 0.18229991843303045, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4767988410999993e-06, "min": 3.4767988410999993e-06, "max": 0.00029528895157035, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0430396523299997e-05, "min": 1.0430396523299997e-05, "max": 0.0008438241187253, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011589, "min": 0.1011589, "max": 0.19842965, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034767, "min": 0.20746960000000003, "max": 0.5812747000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.782911e-05, "min": 6.782911e-05, "max": 0.004921639534999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020348733, "min": 0.00020348733, "max": 0.01406560753, "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": "1671639982", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1671642207" }, "total": 2225.588748587, "count": 1, "self": 0.44218406299978597, "children": { "run_training.setup": { "total": 0.10315604200002326, "count": 1, "self": 0.10315604200002326 }, "TrainerController.start_learning": { "total": 2225.043408482, "count": 1, "self": 3.6580129300873523, "children": { "TrainerController._reset_env": { "total": 8.214664412999923, "count": 1, "self": 8.214664412999923 }, "TrainerController.advance": { "total": 2213.053626870913, "count": 233005, "self": 3.87440091003009, "children": { "env_step": { "total": 1738.911793524996, "count": 233005, "self": 1462.4047868250714, "children": { "SubprocessEnvManager._take_step": { "total": 274.0113999549984, "count": 233005, "self": 14.00192518507481, "children": { "TorchPolicy.evaluate": { "total": 260.0094747699236, "count": 222967, "self": 64.94589537697198, "children": { "TorchPolicy.sample_actions": { "total": 195.06357939295162, "count": 222967, "self": 195.06357939295162 } } } } }, "workers": { "total": 2.4956067449261354, "count": 233005, "self": 0.0, "children": { "worker_root": { "total": 2217.4245353050815, "count": 233005, "is_parallel": true, "self": 1009.0903605890708, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021436990000438527, "count": 1, "is_parallel": true, "self": 0.0003148070001088854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018288919999349673, "count": 2, "is_parallel": true, "self": 0.0018288919999349673 } } }, "UnityEnvironment.step": { "total": 0.028186657999981435, "count": 1, "is_parallel": true, "self": 0.0002748419999534235, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002653029999919454, "count": 1, "is_parallel": true, "self": 0.0002653029999919454 }, "communicator.exchange": { "total": 0.02692190599998412, "count": 1, "is_parallel": true, "self": 0.02692190599998412 }, "steps_from_proto": { "total": 0.0007246070000519467, "count": 1, "is_parallel": true, "self": 0.00025076700001136487, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004738400000405818, "count": 2, "is_parallel": true, "self": 0.0004738400000405818 } } } } } } }, "UnityEnvironment.step": { "total": 1208.3341747160107, "count": 233004, "is_parallel": true, "self": 35.14925396996159, "children": { "UnityEnvironment._generate_step_input": { "total": 75.56769796001288, "count": 233004, "is_parallel": true, "self": 75.56769796001288 }, "communicator.exchange": { "total": 1004.2205096549038, "count": 233004, "is_parallel": true, "self": 1004.2205096549038 }, "steps_from_proto": { "total": 93.39671313113251, "count": 233004, "is_parallel": true, "self": 38.46233577925773, "children": { "_process_rank_one_or_two_observation": { "total": 54.93437735187479, "count": 466008, "is_parallel": true, "self": 54.93437735187479 } } } } } } } } } } }, "trainer_advance": { "total": 470.2674324358866, "count": 233005, "self": 5.957548301777592, "children": { "process_trajectory": { "total": 148.18974438710745, "count": 233005, "self": 146.893335061107, "children": { "RLTrainer._checkpoint": { "total": 1.2964093260004574, "count": 10, "self": 1.2964093260004574 } } }, "_update_policy": { "total": 316.12013974700153, "count": 97, "self": 263.0406506909943, "children": { "TorchPPOOptimizer.update": { "total": 53.07948905600722, "count": 2910, "self": 53.07948905600722 } } } } } } }, "trainer_threads": { "total": 8.520000847056508e-07, "count": 1, "self": 8.520000847056508e-07 }, "TrainerController._save_models": { "total": 0.11710341599973617, "count": 1, "self": 0.002029375999882177, "children": { "RLTrainer._checkpoint": { "total": 0.115074039999854, "count": 1, "self": 0.115074039999854 } } } } } } }