{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8532184362411499, "min": 0.8532184362411499, "max": 2.8357558250427246, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8108.98828125, "min": 8108.98828125, "max": 28947.39453125, "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": 12.948321342468262, "min": 0.4067337214946747, "max": 12.948321342468262, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2524.922607421875, "min": 78.90634155273438, "max": 2611.510986328125, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.08262153714895248, "min": 0.015036159195005894, "max": 0.17223134636878967, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 16.1112003326416, "min": 2.9170148372650146, "max": 35.30742645263672, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07036111243930873, "min": 0.06461285065857274, "max": 0.07399398299985835, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2814444497572349, "min": 0.2642281105845719, "max": 0.36646515682029224, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.11500278202926412, "min": 0.06494965327118395, "max": 0.13927698661299312, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.46001112811705647, "min": 0.2597986130847358, "max": 0.6963849330649656, "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": 0.04110843291980963, "min": 0.04110843291980963, "max": 0.1596157910786204, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.16443373167923853, "min": 0.16443373167923853, "max": 0.6384631643144816, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.7333237435303481, "min": 0.7333237435303481, "max": 2.7372418713628077, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 2.9332949741213925, "min": 2.9332949741213925, "max": 12.594551128499647, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.454545454545453, "min": 3.522727272727273, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 155.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.522727272727273, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 155.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 0.16626568841853773, "min": 0.16626568841853773, "max": 0.35816591313447466, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 7.3156902904156595, "min": 7.3156902904156595, "max": 19.552446191664785, "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": "1739737618", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739738330" }, "total": 712.2876606599999, "count": 1, "self": 0.5368716149998818, "children": { "run_training.setup": { "total": 0.04115984899999603, "count": 1, "self": 0.04115984899999603 }, "TrainerController.start_learning": { "total": 711.709629196, "count": 1, "self": 0.6233477629969002, "children": { "TrainerController._reset_env": { "total": 3.734531887000003, "count": 1, "self": 3.734531887000003 }, "TrainerController.advance": { "total": 707.2546833790033, "count": 18192, "self": 0.6857058919897554, "children": { "env_step": { "total": 385.83271856500016, "count": 18192, "self": 326.78471530399236, "children": { "SubprocessEnvManager._take_step": { "total": 58.68180285201811, "count": 18192, "self": 1.964185440001188, "children": { "TorchPolicy.evaluate": { "total": 56.71761741201692, "count": 18192, "self": 56.71761741201692 } } }, "workers": { "total": 0.3662004089896982, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 709.6123128760091, "count": 18192, "is_parallel": true, "self": 427.61926883900037, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008891065000057097, "count": 1, "is_parallel": true, "self": 0.00607110799990096, "children": { "_process_rank_one_or_two_observation": { "total": 0.002819957000156137, "count": 10, "is_parallel": true, "self": 0.002819957000156137 } } }, "UnityEnvironment.step": { "total": 0.04681298000002698, "count": 1, "is_parallel": true, "self": 0.0007296510000287526, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006947519999584983, "count": 1, "is_parallel": true, "self": 0.0006947519999584983 }, "communicator.exchange": { "total": 0.04314231299997573, "count": 1, "is_parallel": true, "self": 0.04314231299997573 }, "steps_from_proto": { "total": 0.002246264000064002, "count": 1, "is_parallel": true, "self": 0.0004498100000773775, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017964539999866247, "count": 10, "is_parallel": true, "self": 0.0017964539999866247 } } } } } } }, "UnityEnvironment.step": { "total": 281.99304403700876, "count": 18191, "is_parallel": true, "self": 13.65642485003707, "children": { "UnityEnvironment._generate_step_input": { "total": 7.176856220983268, "count": 18191, "is_parallel": true, "self": 7.176856220983268 }, "communicator.exchange": { "total": 220.27470146899623, "count": 18191, "is_parallel": true, "self": 220.27470146899623 }, "steps_from_proto": { "total": 40.88506149699219, "count": 18191, "is_parallel": true, "self": 7.803365305998568, "children": { "_process_rank_one_or_two_observation": { "total": 33.081696190993625, "count": 181910, "is_parallel": true, "self": 33.081696190993625 } } } } } } } } } } }, "trainer_advance": { "total": 320.73625892201335, "count": 18192, "self": 0.7969519829982801, "children": { "process_trajectory": { "total": 45.53306068901418, "count": 18192, "self": 45.01603397401425, "children": { "RLTrainer._checkpoint": { "total": 0.517026714999929, "count": 4, "self": 0.517026714999929 } } }, "_update_policy": { "total": 274.4062462500009, "count": 90, "self": 183.92966783900692, "children": { "TorchPPOOptimizer.update": { "total": 90.47657841099397, "count": 4587, "self": 90.47657841099397 } } } } } } }, "trainer_threads": { "total": 1.0869998732232489e-06, "count": 1, "self": 1.0869998732232489e-06 }, "TrainerController._save_models": { "total": 0.09706507999999303, "count": 1, "self": 0.0011365120001300966, "children": { "RLTrainer._checkpoint": { "total": 0.09592856799986293, "count": 1, "self": 0.09592856799986293 } } } } } } }