{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4037299156188965, "min": 1.4037299156188965, "max": 1.4276964664459229, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68770.1328125, "min": 68770.1328125, "max": 76422.0234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 105.10191082802548, "min": 102.35378323108384, "max": 363.62589928057554, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49503.0, "min": 48989.0, "max": 50544.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999906.0, "min": 49933.0, "max": 1999906.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999906.0, "min": 49933.0, "max": 1999906.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.306583881378174, "min": 0.06502743065357208, "max": 2.364840269088745, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1086.4010009765625, "min": 8.973785400390625, "max": 1146.9464111328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5365252492281027, "min": 1.7338803235603415, "max": 3.7579018556636217, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1665.7033923864365, "min": 239.27548465132713, "max": 1780.8182772994041, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5365252492281027, "min": 1.7338803235603415, "max": 3.7579018556636217, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1665.7033923864365, "min": 239.27548465132713, "max": 1780.8182772994041, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0188173357208143, "min": 0.013606221536873716, "max": 0.022031554040828877, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0376346714416286, "min": 0.029068732588590745, "max": 0.06165428824800377, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05176851848761241, "min": 0.022327616189916927, "max": 0.06089926964292924, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10353703697522482, "min": 0.044655232379833855, "max": 0.1723736647516489, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.168298610600006e-06, "min": 4.168298610600006e-06, "max": 0.0002953600515466499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.336597221200012e-06, "min": 8.336597221200012e-06, "max": 0.0008436427687857499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10138939999999999, "min": 0.10138939999999999, "max": 0.19845334999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20277879999999998, "min": 0.20277879999999998, "max": 0.5812142500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.93310600000001e-05, "min": 7.93310600000001e-05, "max": 0.004922822164999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001586621200000002, "min": 0.0001586621200000002, "max": 0.014062591075, "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": "1670957612", "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=Huggy2 --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": "1670959721" }, "total": 2108.590958064, "count": 1, "self": 0.42329716400035977, "children": { "run_training.setup": { "total": 0.102134230999809, "count": 1, "self": 0.102134230999809 }, "TrainerController.start_learning": { "total": 2108.065526669, "count": 1, "self": 3.610653050068777, "children": { "TrainerController._reset_env": { "total": 6.003229919999967, "count": 1, "self": 6.003229919999967 }, "TrainerController.advance": { "total": 2098.3329733319315, "count": 230514, "self": 3.918648490940541, "children": { "env_step": { "total": 1655.193032296945, "count": 230514, "self": 1390.0551211128043, "children": { "SubprocessEnvManager._take_step": { "total": 262.61886315802826, "count": 230514, "self": 13.724620592947758, "children": { "TorchPolicy.evaluate": { "total": 248.8942425650805, "count": 222877, "self": 63.19002566919221, "children": { "TorchPolicy.sample_actions": { "total": 185.7042168958883, "count": 222877, "self": 185.7042168958883 } } } } }, "workers": { "total": 2.5190480261123867, "count": 230514, "self": 0.0, "children": { "worker_root": { "total": 2100.5296902990817, "count": 230514, "is_parallel": true, "self": 957.5579792281769, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010236789998998574, "count": 1, "is_parallel": true, "self": 0.0003975599997829704, "children": { "_process_rank_one_or_two_observation": { "total": 0.000626119000116887, "count": 2, "is_parallel": true, "self": 0.000626119000116887 } } }, "UnityEnvironment.step": { "total": 0.026182786000163105, "count": 1, "is_parallel": true, "self": 0.0002527620001728792, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017507100005786924, "count": 1, "is_parallel": true, "self": 0.00017507100005786924 }, "communicator.exchange": { "total": 0.024863592999963657, "count": 1, "is_parallel": true, "self": 0.024863592999963657 }, "steps_from_proto": { "total": 0.0008913599999686994, "count": 1, "is_parallel": true, "self": 0.00023072700014381553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006606329998248839, "count": 2, "is_parallel": true, "self": 0.0006606329998248839 } } } } } } }, "UnityEnvironment.step": { "total": 1142.9717110709048, "count": 230513, "is_parallel": true, "self": 33.664489930812806, "children": { "UnityEnvironment._generate_step_input": { "total": 73.69774333100509, "count": 230513, "is_parallel": true, "self": 73.69774333100509 }, "communicator.exchange": { "total": 945.6477998410908, "count": 230513, "is_parallel": true, "self": 945.6477998410908 }, "steps_from_proto": { "total": 89.96167796799614, "count": 230513, "is_parallel": true, "self": 37.17214223489236, "children": { "_process_rank_one_or_two_observation": { "total": 52.789535733103776, "count": 461026, "is_parallel": true, "self": 52.789535733103776 } } } } } } } } } } }, "trainer_advance": { "total": 439.22129254404604, "count": 230514, "self": 5.576811211966287, "children": { "process_trajectory": { "total": 132.26752881708012, "count": 230514, "self": 131.77097565007966, "children": { "RLTrainer._checkpoint": { "total": 0.4965531670004566, "count": 4, "self": 0.4965531670004566 } } }, "_update_policy": { "total": 301.37695251499963, "count": 96, "self": 249.65281393298733, "children": { "TorchPPOOptimizer.update": { "total": 51.7241385820123, "count": 2880, "self": 51.7241385820123 } } } } } } }, "trainer_threads": { "total": 9.559998943586834e-07, "count": 1, "self": 9.559998943586834e-07 }, "TrainerController._save_models": { "total": 0.11866941099970063, "count": 1, "self": 0.002043199999661738, "children": { "RLTrainer._checkpoint": { "total": 0.11662621100003889, "count": 1, "self": 0.11662621100003889 } } } } } } }