{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.052049994468689, "min": 1.052049994468689, "max": 2.8765931129455566, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10114.408203125, "min": 10114.408203125, "max": 29554.1171875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.53941535949707, "min": 0.2404416799545288, "max": 12.53941535949707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2445.18603515625, "min": 46.645687103271484, "max": 2516.744873046875, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.30715563893318176, "min": 0.13454927504062653, "max": 0.33984506130218506, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 59.895347595214844, "min": 26.10256004333496, "max": 69.3283920288086, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06624198280384436, "min": 0.05941402768190065, "max": 0.07298021745872592, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26496793121537743, "min": 0.2376561107276026, "max": 0.3649010872936296, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1111151895613647, "min": 0.05328787249220791, "max": 0.14038343807938053, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4444607582454588, "min": 0.21315148996883165, "max": 0.6862502733574194, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.059867350731556315, "min": 0.04376971360807326, "max": 0.19692793819943774, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.23946940292622526, "min": 0.2188485680403663, "max": 0.787711752797751, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.974638027303359, "min": 0.974638027303359, "max": 2.880710300423351, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 3.898552109213436, "min": 3.898552109213436, "max": 13.749294056611902, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.136363636363637, "min": 2.9318181818181817, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 129.0, "max": 1355.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 2.9318181818181817, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 129.0, "max": 1355.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 0.6016799750822511, "min": 0.4373950545252724, "max": 1.1356272992931984, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 26.47391890361905, "min": 24.056727998889983, "max": 49.96760116890073, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688606107", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1688606629" }, "total": 522.0203890309999, "count": 1, "self": 0.44034017900003164, "children": { "run_training.setup": { "total": 0.042045011000027444, "count": 1, "self": 0.042045011000027444 }, "TrainerController.start_learning": { "total": 521.5380038409999, "count": 1, "self": 0.5414292410050621, "children": { "TrainerController._reset_env": { "total": 5.082364999999754, "count": 1, "self": 5.082364999999754 }, "TrainerController.advance": { "total": 515.7753534789949, "count": 18207, "self": 0.25979930094763404, "children": { "env_step": { "total": 515.5155541780473, "count": 18207, "self": 399.238631631059, "children": { "SubprocessEnvManager._take_step": { "total": 116.00677036401157, "count": 18207, "self": 1.6173548020469752, "children": { "TorchPolicy.evaluate": { "total": 114.3894155619646, "count": 18207, "self": 114.3894155619646 } } }, "workers": { "total": 0.27015218297674437, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 519.800899042019, "count": 18207, "is_parallel": true, "self": 277.18311499900346, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056549260002611845, "count": 1, "is_parallel": true, "self": 0.003984032999142073, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016708930011191114, "count": 10, "is_parallel": true, "self": 0.0016708930011191114 } } }, "UnityEnvironment.step": { "total": 0.07883530299977792, "count": 1, "is_parallel": true, "self": 0.0006627959996876598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004485510003178206, "count": 1, "is_parallel": true, "self": 0.0004485510003178206 }, "communicator.exchange": { "total": 0.06608355999969717, "count": 1, "is_parallel": true, "self": 0.06608355999969717 }, "steps_from_proto": { "total": 0.01164039600007527, "count": 1, "is_parallel": true, "self": 0.01004649999913454, "children": { "_process_rank_one_or_two_observation": { "total": 0.001593896000940731, "count": 10, "is_parallel": true, "self": 0.001593896000940731 } } } } } } }, "UnityEnvironment.step": { "total": 242.6177840430155, "count": 18206, "is_parallel": true, "self": 9.995710548943862, "children": { "UnityEnvironment._generate_step_input": { "total": 5.179248844004633, "count": 18206, "is_parallel": true, "self": 5.179248844004633 }, "communicator.exchange": { "total": 193.7130021610369, "count": 18206, "is_parallel": true, "self": 193.7130021610369 }, "steps_from_proto": { "total": 33.729822489030084, "count": 18206, "is_parallel": true, "self": 6.126066661098321, "children": { "_process_rank_one_or_two_observation": { "total": 27.603755827931764, "count": 182060, "is_parallel": true, "self": 27.603755827931764 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012937300016346853, "count": 1, "self": 0.00012937300016346853, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 512.6990198097396, "count": 398710, "is_parallel": true, "self": 8.364893935884083, "children": { "process_trajectory": { "total": 262.1327037428523, "count": 398710, "is_parallel": true, "self": 260.91627016085295, "children": { "RLTrainer._checkpoint": { "total": 1.216433581999354, "count": 4, "is_parallel": true, "self": 1.216433581999354 } } }, "_update_policy": { "total": 242.20142213100326, "count": 90, "is_parallel": true, "self": 148.7243393410049, "children": { "TorchPPOOptimizer.update": { "total": 93.47708278999835, "count": 4587, "is_parallel": true, "self": 93.47708278999835 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13872674799995366, "count": 1, "self": 0.0006833979996372364, "children": { "RLTrainer._checkpoint": { "total": 0.13804335000031642, "count": 1, "self": 0.13804335000031642 } } } } } } }