{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.399922490119934, "min": 1.399922490119934, "max": 1.4280250072479248, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69847.734375, "min": 68224.2109375, "max": 79584.359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.91145833333333, "min": 81.04926108374384, "max": 399.0, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49485.0, "min": 48802.0, "max": 50163.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999989.0, "min": 49633.0, "max": 1999989.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999989.0, "min": 49633.0, "max": 1999989.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.504275321960449, "min": 0.1371791511774063, "max": 2.504275321960449, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1442.4625244140625, "min": 17.01021385192871, "max": 1500.39990234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9167579167212048, "min": 1.7470310988926119, "max": 3.979216912373144, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2256.052560031414, "min": 216.63185626268387, "max": 2334.161261498928, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9167579167212048, "min": 1.7470310988926119, "max": 3.979216912373144, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2256.052560031414, "min": 216.63185626268387, "max": 2334.161261498928, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01486557094896044, "min": 0.01411254000122426, "max": 0.020325877122862344, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04459671284688132, "min": 0.02822508000244852, "max": 0.05868399599567056, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054611511735452554, "min": 0.021922580183794102, "max": 0.0628659322236975, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16383453520635766, "min": 0.043845160367588204, "max": 0.1812916599214077, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6196487934833377e-06, "min": 3.6196487934833377e-06, "max": 0.000295338826553725, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0858946380450013e-05, "min": 1.0858946380450013e-05, "max": 0.0008441632686122498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120651666666668, "min": 0.10120651666666668, "max": 0.19844627500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30361955, "min": 0.20754595, "max": 0.5813877499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.020518166666675e-05, "min": 7.020518166666675e-05, "max": 0.004922469122500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021061554500000025, "min": 0.00021061554500000025, "max": 0.014071248725000002, "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": "1676600443", "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": "1676602848" }, "total": 2404.665479332, "count": 1, "self": 0.43095346800009793, "children": { "run_training.setup": { "total": 0.17873394299999745, "count": 1, "self": 0.17873394299999745 }, "TrainerController.start_learning": { "total": 2404.055791921, "count": 1, "self": 4.09522851900374, "children": { "TrainerController._reset_env": { "total": 10.887471233999975, "count": 1, "self": 10.887471233999975 }, "TrainerController.advance": { "total": 2388.957205934996, "count": 232553, "self": 4.379952381939802, "children": { "env_step": { "total": 1854.3720257061227, "count": 232553, "self": 1552.6187789573066, "children": { "SubprocessEnvManager._take_step": { "total": 299.0018081528606, "count": 232553, "self": 15.410334960864986, "children": { "TorchPolicy.evaluate": { "total": 283.5914731919956, "count": 222946, "self": 70.74359552398681, "children": { "TorchPolicy.sample_actions": { "total": 212.84787766800878, "count": 222946, "self": 212.84787766800878 } } } } }, "workers": { "total": 2.7514385959555057, "count": 232553, "self": 0.0, "children": { "worker_root": { "total": 2395.6778159171026, "count": 232553, "is_parallel": true, "self": 1129.576190962139, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029684650000376678, "count": 1, "is_parallel": true, "self": 0.0004683170000703285, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025001479999673393, "count": 2, "is_parallel": true, "self": 0.0025001479999673393 } } }, "UnityEnvironment.step": { "total": 0.028639402999999675, "count": 1, "is_parallel": true, "self": 0.0002909189999513728, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002231710000160092, "count": 1, "is_parallel": true, "self": 0.0002231710000160092 }, "communicator.exchange": { "total": 0.027436679999993885, "count": 1, "is_parallel": true, "self": 0.027436679999993885 }, "steps_from_proto": { "total": 0.0006886330000384078, "count": 1, "is_parallel": true, "self": 0.00021344300000691874, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047519000003148903, "count": 2, "is_parallel": true, "self": 0.00047519000003148903 } } } } } } }, "UnityEnvironment.step": { "total": 1266.1016249549637, "count": 232552, "is_parallel": true, "self": 38.26444529189507, "children": { "UnityEnvironment._generate_step_input": { "total": 80.4257013839707, "count": 232552, "is_parallel": true, "self": 80.4257013839707 }, "communicator.exchange": { "total": 1054.4831855191103, "count": 232552, "is_parallel": true, "self": 1054.4831855191103 }, "steps_from_proto": { "total": 92.92829275998736, "count": 232552, "is_parallel": true, "self": 38.005457724932796, "children": { "_process_rank_one_or_two_observation": { "total": 54.92283503505456, "count": 465104, "is_parallel": true, "self": 54.92283503505456 } } } } } } } } } } }, "trainer_advance": { "total": 530.2052278469337, "count": 232553, "self": 6.367015955898296, "children": { "process_trajectory": { "total": 165.41059149003758, "count": 232553, "self": 164.03530921303746, "children": { "RLTrainer._checkpoint": { "total": 1.3752822770001103, "count": 10, "self": 1.3752822770001103 } } }, "_update_policy": { "total": 358.42762040099785, "count": 97, "self": 300.87838460498574, "children": { "TorchPPOOptimizer.update": { "total": 57.54923579601211, "count": 2910, "self": 57.54923579601211 } } } } } } }, "trainer_threads": { "total": 9.330001375928987e-07, "count": 1, "self": 9.330001375928987e-07 }, "TrainerController._save_models": { "total": 0.11588530000017272, "count": 1, "self": 0.0028414349999366095, "children": { "RLTrainer._checkpoint": { "total": 0.11304386500023611, "count": 1, "self": 0.11304386500023611 } } } } } } }