{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408214807510376, "min": 1.4082095623016357, "max": 1.426234483718872, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70837.4296875, "min": 67894.6015625, "max": 75870.4921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.67592592592592, "min": 83.1902356902357, "max": 395.18897637795277, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49505.0, "min": 49213.0, "max": 50189.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999983.0, "min": 49762.0, "max": 1999983.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999983.0, "min": 49762.0, "max": 1999983.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3520827293395996, "min": 0.07439877837896347, "max": 2.449077606201172, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1270.1246337890625, "min": 9.374245643615723, "max": 1409.3056640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6289478583468333, "min": 1.8221262206160833, "max": 3.9786933276537204, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1959.63184350729, "min": 229.5879037976265, "max": 2224.439033269882, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6289478583468333, "min": 1.8221262206160833, "max": 3.9786933276537204, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1959.63184350729, "min": 229.5879037976265, "max": 2224.439033269882, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015552002132810433, "min": 0.014103835088705333, "max": 0.019338696725511303, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0466560063984313, "min": 0.028207670177410667, "max": 0.05801609017653391, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05460291161305375, "min": 0.02261876535291473, "max": 0.05762432151370578, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16380873483916125, "min": 0.04523753070582946, "max": 0.17287296454111734, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2763989079000094e-06, "min": 3.2763989079000094e-06, "max": 0.0002953197015601, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.829196723700029e-06, "min": 9.829196723700029e-06, "max": 0.0008440474686508498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109210000000002, "min": 0.10109210000000002, "max": 0.19843990000000009, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30327630000000005, "min": 0.2073684, "max": 0.5813491499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.449579000000018e-05, "min": 6.449579000000018e-05, "max": 0.0049221510100000004, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019348737000000053, "min": 0.00019348737000000053, "max": 0.014069322585, "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": "1696343010", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1696345531" }, "total": 2520.440615486, "count": 1, "self": 0.4864965540000412, "children": { "run_training.setup": { "total": 0.04721437099999548, "count": 1, "self": 0.04721437099999548 }, "TrainerController.start_learning": { "total": 2519.906904561, "count": 1, "self": 4.542148669921517, "children": { "TrainerController._reset_env": { "total": 5.323324802000002, "count": 1, "self": 5.323324802000002 }, "TrainerController.advance": { "total": 2509.9112190820783, "count": 232121, "self": 4.740638320274229, "children": { "env_step": { "total": 1939.0318667348859, "count": 232121, "self": 1639.1278240659299, "children": { "SubprocessEnvManager._take_step": { "total": 296.9875637849952, "count": 232121, "self": 17.131729676910993, "children": { "TorchPolicy.evaluate": { "total": 279.8558341080842, "count": 222994, "self": 279.8558341080842 } } }, "workers": { "total": 2.9164788839607354, "count": 232121, "self": 0.0, "children": { "worker_root": { "total": 2512.2788562851115, "count": 232121, "is_parallel": true, "self": 1169.4381050650525, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009989919999497943, "count": 1, "is_parallel": true, "self": 0.00028638999992836034, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007126020000214339, "count": 2, "is_parallel": true, "self": 0.0007126020000214339 } } }, "UnityEnvironment.step": { "total": 0.05908514899999773, "count": 1, "is_parallel": true, "self": 0.00037905100003854386, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002410359999771572, "count": 1, "is_parallel": true, "self": 0.0002410359999771572 }, "communicator.exchange": { "total": 0.05756813300001795, "count": 1, "is_parallel": true, "self": 0.05756813300001795 }, "steps_from_proto": { "total": 0.000896928999964075, "count": 1, "is_parallel": true, "self": 0.00026585399996292836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006310750000011467, "count": 2, "is_parallel": true, "self": 0.0006310750000011467 } } } } } } }, "UnityEnvironment.step": { "total": 1342.840751220059, "count": 232120, "is_parallel": true, "self": 41.70353378903155, "children": { "UnityEnvironment._generate_step_input": { "total": 84.32887638799951, "count": 232120, "is_parallel": true, "self": 84.32887638799951 }, "communicator.exchange": { "total": 1113.8199303270644, "count": 232120, "is_parallel": true, "self": 1113.8199303270644 }, "steps_from_proto": { "total": 102.98841071596348, "count": 232120, "is_parallel": true, "self": 37.02919667088884, "children": { "_process_rank_one_or_two_observation": { "total": 65.95921404507465, "count": 464240, "is_parallel": true, "self": 65.95921404507465 } } } } } } } } } } }, "trainer_advance": { "total": 566.1387140269183, "count": 232121, "self": 6.785737372888207, "children": { "process_trajectory": { "total": 139.47772236002902, "count": 232121, "self": 137.8214239350292, "children": { "RLTrainer._checkpoint": { "total": 1.656298424999818, "count": 10, "self": 1.656298424999818 } } }, "_update_policy": { "total": 419.875254294001, "count": 97, "self": 358.3052649649961, "children": { "TorchPPOOptimizer.update": { "total": 61.5699893290049, "count": 2910, "self": 61.5699893290049 } } } } } } }, "trainer_threads": { "total": 1.5319997146434616e-06, "count": 1, "self": 1.5319997146434616e-06 }, "TrainerController._save_models": { "total": 0.13021047500023997, "count": 1, "self": 0.002111666000018886, "children": { "RLTrainer._checkpoint": { "total": 0.12809880900022108, "count": 1, "self": 0.12809880900022108 } } } } } } }