{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4061048030853271, "min": 1.4061048030853271, "max": 1.4293618202209473, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70568.1796875, "min": 68775.125, "max": 76349.859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.30929791271348, "min": 74.09009009009009, "max": 420.06666666666666, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49174.0, "min": 48834.0, "max": 50408.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999254.0, "min": 49848.0, "max": 1999254.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999254.0, "min": 49848.0, "max": 1999254.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5037641525268555, "min": 0.09084034711122513, "max": 2.5080296993255615, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1319.4837646484375, "min": 10.810001373291016, "max": 1638.906005859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.828609245778035, "min": 1.7253930956876578, "max": 4.011274139436198, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2017.6770725250244, "min": 205.32177838683128, "max": 2579.5684235692024, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.828609245778035, "min": 1.7253930956876578, "max": 4.011274139436198, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2017.6770725250244, "min": 205.32177838683128, "max": 2579.5684235692024, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018209458475596168, "min": 0.014207910032079477, "max": 0.01969848735607229, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0546283754267885, "min": 0.030475717317555488, "max": 0.0546283754267885, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05006264224648476, "min": 0.022879877034574746, "max": 0.06480103911211094, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15018792673945427, "min": 0.04575975406914949, "max": 0.1799713918318351, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.865048711683334e-06, "min": 3.865048711683334e-06, "max": 0.0002953483515505499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1595146135050002e-05, "min": 1.1595146135050002e-05, "max": 0.0008442463685845499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012883166666667, "min": 0.1012883166666667, "max": 0.19844945000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038649500000001, "min": 0.20771065000000002, "max": 0.58141545, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.428700166666667e-05, "min": 7.428700166666667e-05, "max": 0.0049226275550000006, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000222861005, "min": 0.000222861005, "max": 0.014072630955000002, "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": "1671297417", "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": "1671299540" }, "total": 2122.563922687, "count": 1, "self": 0.45914026599984936, "children": { "run_training.setup": { "total": 0.11663059299996803, "count": 1, "self": 0.11663059299996803 }, "TrainerController.start_learning": { "total": 2121.988151828, "count": 1, "self": 3.6285961650455647, "children": { "TrainerController._reset_env": { "total": 6.980869005000045, "count": 1, "self": 6.980869005000045 }, "TrainerController.advance": { "total": 2111.250068276954, "count": 233170, "self": 3.9861591721096374, "children": { "env_step": { "total": 1647.5998994589806, "count": 233170, "self": 1384.059507550986, "children": { "SubprocessEnvManager._take_step": { "total": 261.13714874897903, "count": 233170, "self": 13.604636140889625, "children": { "TorchPolicy.evaluate": { "total": 247.5325126080894, "count": 223012, "self": 62.12093045917857, "children": { "TorchPolicy.sample_actions": { "total": 185.41158214891084, "count": 223012, "self": 185.41158214891084 } } } } }, "workers": { "total": 2.403243159015801, "count": 233170, "self": 0.0, "children": { "worker_root": { "total": 2114.490057409938, "count": 233170, "is_parallel": true, "self": 977.0699123200332, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002022893000003023, "count": 1, "is_parallel": true, "self": 0.00032770500001788605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016951879999851371, "count": 2, "is_parallel": true, "self": 0.0016951879999851371 } } }, "UnityEnvironment.step": { "total": 0.03017283999997744, "count": 1, "is_parallel": true, "self": 0.0003129720000742964, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001871929999879285, "count": 1, "is_parallel": true, "self": 0.0001871929999879285 }, "communicator.exchange": { "total": 0.028892907999988893, "count": 1, "is_parallel": true, "self": 0.028892907999988893 }, "steps_from_proto": { "total": 0.0007797669999263235, "count": 1, "is_parallel": true, "self": 0.00027865399988513673, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005011130000411868, "count": 2, "is_parallel": true, "self": 0.0005011130000411868 } } } } } } }, "UnityEnvironment.step": { "total": 1137.4201450899047, "count": 233169, "is_parallel": true, "self": 33.33044799002437, "children": { "UnityEnvironment._generate_step_input": { "total": 72.81516488590933, "count": 233169, "is_parallel": true, "self": 72.81516488590933 }, "communicator.exchange": { "total": 941.3944284119888, "count": 233169, "is_parallel": true, "self": 941.3944284119888 }, "steps_from_proto": { "total": 89.88010380198227, "count": 233169, "is_parallel": true, "self": 36.8631246808859, "children": { "_process_rank_one_or_two_observation": { "total": 53.01697912109637, "count": 466338, "is_parallel": true, "self": 53.01697912109637 } } } } } } } } } } }, "trainer_advance": { "total": 459.66400964586387, "count": 233170, "self": 5.380786114773059, "children": { "process_trajectory": { "total": 144.77483586309324, "count": 233170, "self": 143.63429989509268, "children": { "RLTrainer._checkpoint": { "total": 1.1405359680005631, "count": 10, "self": 1.1405359680005631 } } }, "_update_policy": { "total": 309.50838766799757, "count": 97, "self": 257.36364231099435, "children": { "TorchPPOOptimizer.update": { "total": 52.14474535700322, "count": 2910, "self": 52.14474535700322 } } } } } } }, "trainer_threads": { "total": 8.679999154992402e-07, "count": 1, "self": 8.679999154992402e-07 }, "TrainerController._save_models": { "total": 0.12861751300033575, "count": 1, "self": 0.0028382640002746484, "children": { "RLTrainer._checkpoint": { "total": 0.1257792490000611, "count": 1, "self": 0.1257792490000611 } } } } } } }