{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4042881727218628, "min": 1.4042881727218628, "max": 1.4251763820648193, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70411.0078125, "min": 68225.28125, "max": 78130.4453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.7834862385321, "min": 87.89342806394316, "max": 388.8837209302326, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49477.0, "min": 48781.0, "max": 50166.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999974.0, "min": 49772.0, "max": 1999974.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999974.0, "min": 49772.0, "max": 1999974.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3745720386505127, "min": -0.00994320958852768, "max": 2.4730424880981445, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1294.1417236328125, "min": -1.272730827331543, "max": 1347.029541015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7011775265046216, "min": 1.8427415963960811, "max": 3.890451140525773, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2017.1417519450188, "min": 235.8709243386984, "max": 2109.2991265058517, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7011775265046216, "min": 1.8427415963960811, "max": 3.890451140525773, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2017.1417519450188, "min": 235.8709243386984, "max": 2109.2991265058517, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016379139009869606, "min": 0.013307832402157754, "max": 0.021352459672683226, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04913741702960882, "min": 0.026615664804315507, "max": 0.057836800960164206, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056198360108666946, "min": 0.022776084889968237, "max": 0.05986976101994514, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16859508032600085, "min": 0.04555216977993647, "max": 0.17960928305983542, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4694488435499925e-06, "min": 3.4694488435499925e-06, "max": 0.000295288426570525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0408346530649977e-05, "min": 1.0408346530649977e-05, "max": 0.0008440555686481501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115645, "min": 0.10115645, "max": 0.19842947499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30346934999999997, "min": 0.20746199999999998, "max": 0.5813518500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.77068549999999e-05, "min": 6.77068549999999e-05, "max": 0.004921630802499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002031205649999997, "min": 0.0002031205649999997, "max": 0.014069457314999997, "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": "1675116960", "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": "1.21.6", "end_time_seconds": "1675119063" }, "total": 2103.469403002, "count": 1, "self": 0.43696345299986206, "children": { "run_training.setup": { "total": 0.10213307999998733, "count": 1, "self": 0.10213307999998733 }, "TrainerController.start_learning": { "total": 2102.9303064690002, "count": 1, "self": 3.6878703419870362, "children": { "TrainerController._reset_env": { "total": 9.743806151000001, "count": 1, "self": 9.743806151000001 }, "TrainerController.advance": { "total": 2089.3924656730132, "count": 231624, "self": 4.008023365970075, "children": { "env_step": { "total": 1645.6639882340535, "count": 231624, "self": 1380.0714411961108, "children": { "SubprocessEnvManager._take_step": { "total": 263.03221083593644, "count": 231624, "self": 13.606856580928365, "children": { "TorchPolicy.evaluate": { "total": 249.42535425500807, "count": 222862, "self": 62.71836882007403, "children": { "TorchPolicy.sample_actions": { "total": 186.70698543493404, "count": 222862, "self": 186.70698543493404 } } } } }, "workers": { "total": 2.5603362020061695, "count": 231624, "self": 0.0, "children": { "worker_root": { "total": 2095.5840388080387, "count": 231624, "is_parallel": true, "self": 959.7695782740168, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024095489999922393, "count": 1, "is_parallel": true, "self": 0.0003834610000126304, "children": { "_process_rank_one_or_two_observation": { "total": 0.002026087999979609, "count": 2, "is_parallel": true, "self": 0.002026087999979609 } } }, "UnityEnvironment.step": { "total": 0.026632720999998583, "count": 1, "is_parallel": true, "self": 0.00026022000002967616, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002143410000030599, "count": 1, "is_parallel": true, "self": 0.0002143410000030599 }, "communicator.exchange": { "total": 0.02520290100000011, "count": 1, "is_parallel": true, "self": 0.02520290100000011 }, "steps_from_proto": { "total": 0.0009552589999657357, "count": 1, "is_parallel": true, "self": 0.00022657499999922948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007286839999665062, "count": 2, "is_parallel": true, "self": 0.0007286839999665062 } } } } } } }, "UnityEnvironment.step": { "total": 1135.814460534022, "count": 231623, "is_parallel": true, "self": 32.80253531298149, "children": { "UnityEnvironment._generate_step_input": { "total": 73.55880427800457, "count": 231623, "is_parallel": true, "self": 73.55880427800457 }, "communicator.exchange": { "total": 938.1228605919825, "count": 231623, "is_parallel": true, "self": 938.1228605919825 }, "steps_from_proto": { "total": 91.33026035105331, "count": 231623, "is_parallel": true, "self": 35.722767810265054, "children": { "_process_rank_one_or_two_observation": { "total": 55.60749254078826, "count": 463246, "is_parallel": true, "self": 55.60749254078826 } } } } } } } } } } }, "trainer_advance": { "total": 439.7204540729899, "count": 231624, "self": 5.528049104902891, "children": { "process_trajectory": { "total": 138.18086670408667, "count": 231624, "self": 137.1054780040867, "children": { "RLTrainer._checkpoint": { "total": 1.0753886999999622, "count": 10, "self": 1.0753886999999622 } } }, "_update_policy": { "total": 296.01153826400036, "count": 97, "self": 243.5741424360001, "children": { "TorchPPOOptimizer.update": { "total": 52.43739582800026, "count": 2910, "self": 52.43739582800026 } } } } } } }, "trainer_threads": { "total": 8.199999683711212e-07, "count": 1, "self": 8.199999683711212e-07 }, "TrainerController._save_models": { "total": 0.10616348299981837, "count": 1, "self": 0.001986045999728958, "children": { "RLTrainer._checkpoint": { "total": 0.10417743700008941, "count": 1, "self": 0.10417743700008941 } } } } } } }