{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4015079736709595, "min": 1.4015079736709595, "max": 1.4257482290267944, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68243.625, "min": 68017.6953125, "max": 77038.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.26548672566372, "min": 77.84858044164038, "max": 397.7857142857143, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48740.0, "min": 48740.0, "max": 50130.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999894.0, "min": 49834.0, "max": 1999894.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999894.0, "min": 49834.0, "max": 1999894.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.411029577255249, "min": 0.1132083311676979, "max": 2.4661686420440674, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1362.231689453125, "min": 14.151041030883789, "max": 1549.318115234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6792388248232615, "min": 1.8422050627470017, "max": 3.955671088470892, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2078.7699360251427, "min": 230.2756328433752, "max": 2447.551071226597, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6792388248232615, "min": 1.8422050627470017, "max": 3.955671088470892, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2078.7699360251427, "min": 230.2756328433752, "max": 2447.551071226597, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019055055963852083, "min": 0.012797293163021096, "max": 0.0190777805109974, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05716516789155625, "min": 0.02895740675739944, "max": 0.05716516789155625, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05187031225197845, "min": 0.02196466826523344, "max": 0.06156777236610651, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15561093675593535, "min": 0.04392933653046688, "max": 0.17847657812138398, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6453987848999946e-06, "min": 3.6453987848999946e-06, "max": 0.0002953463265512249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0936196354699984e-05, "min": 1.0936196354699984e-05, "max": 0.0008440011186663001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012151, "min": 0.1012151, "max": 0.19844877499999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036453, "min": 0.20757354999999994, "max": 0.5813337000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.063348999999994e-05, "min": 7.063348999999994e-05, "max": 0.0049225938725000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002119004699999998, "min": 0.0002119004699999998, "max": 0.01406855163, "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": "1670420430", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670422614" }, "total": 2184.542498956, "count": 1, "self": 0.3916655250000076, "children": { "run_training.setup": { "total": 0.1117674839999836, "count": 1, "self": 0.1117674839999836 }, "TrainerController.start_learning": { "total": 2184.0390659470004, "count": 1, "self": 3.9006181590493725, "children": { "TrainerController._reset_env": { "total": 9.607339628000034, "count": 1, "self": 9.607339628000034 }, "TrainerController.advance": { "total": 2170.4066134969507, "count": 232266, "self": 3.9760620100078086, "children": { "env_step": { "total": 1706.1483784439995, "count": 232266, "self": 1425.34543876493, "children": { "SubprocessEnvManager._take_step": { "total": 278.3204733029913, "count": 232266, "self": 14.688086501975647, "children": { "TorchPolicy.evaluate": { "total": 263.6323868010156, "count": 222908, "self": 67.41192983596483, "children": { "TorchPolicy.sample_actions": { "total": 196.2204569650508, "count": 222908, "self": 196.2204569650508 } } } } }, "workers": { "total": 2.482466376078264, "count": 232266, "self": 0.0, "children": { "worker_root": { "total": 2176.1342255750455, "count": 232266, "is_parallel": true, "self": 1000.0773549070493, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017041579999954592, "count": 1, "is_parallel": true, "self": 0.00031138499997496183, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013927730000204974, "count": 2, "is_parallel": true, "self": 0.0013927730000204974 } } }, "UnityEnvironment.step": { "total": 0.040293818000009196, "count": 1, "is_parallel": true, "self": 0.00031248899995262036, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0034848239999973885, "count": 1, "is_parallel": true, "self": 0.0034848239999973885 }, "communicator.exchange": { "total": 0.03579495000002453, "count": 1, "is_parallel": true, "self": 0.03579495000002453 }, "steps_from_proto": { "total": 0.0007015550000346593, "count": 1, "is_parallel": true, "self": 0.0002250940000863011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004764609999483582, "count": 2, "is_parallel": true, "self": 0.0004764609999483582 } } } } } } }, "UnityEnvironment.step": { "total": 1176.0568706679962, "count": 232265, "is_parallel": true, "self": 34.18224094389075, "children": { "UnityEnvironment._generate_step_input": { "total": 73.91529536900032, "count": 232265, "is_parallel": true, "self": 73.91529536900032 }, "communicator.exchange": { "total": 976.5750589110276, "count": 232265, "is_parallel": true, "self": 976.5750589110276 }, "steps_from_proto": { "total": 91.38427544407756, "count": 232265, "is_parallel": true, "self": 37.71387766202088, "children": { "_process_rank_one_or_two_observation": { "total": 53.67039778205668, "count": 464530, "is_parallel": true, "self": 53.67039778205668 } } } } } } } } } } }, "trainer_advance": { "total": 460.28217304294367, "count": 232266, "self": 5.886440661025233, "children": { "process_trajectory": { "total": 149.8727472519182, "count": 232266, "self": 149.40290941791795, "children": { "RLTrainer._checkpoint": { "total": 0.46983783400025914, "count": 4, "self": 0.46983783400025914 } } }, "_update_policy": { "total": 304.5229851300002, "count": 97, "self": 250.48545608600818, "children": { "TorchPPOOptimizer.update": { "total": 54.03752904399204, "count": 2910, "self": 54.03752904399204 } } } } } } }, "trainer_threads": { "total": 1.0430003385408781e-06, "count": 1, "self": 1.0430003385408781e-06 }, "TrainerController._save_models": { "total": 0.12449362000006658, "count": 1, "self": 0.0019298419997539895, "children": { "RLTrainer._checkpoint": { "total": 0.1225637780003126, "count": 1, "self": 0.1225637780003126 } } } } } } }