{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9355095624923706, "min": 0.9355095624923706, "max": 2.8586983680725098, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8963.1171875, "min": 8963.1171875, "max": 29338.8203125, "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": 12.792675971984863, "min": 0.2781604826450348, "max": 12.792675971984863, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2494.57177734375, "min": 53.963130950927734, "max": 2577.061767578125, "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.Losses.PolicyLoss.mean": { "value": 0.07127476943134181, "min": 0.06178741210226458, "max": 0.07691625120136122, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28509907772536724, "min": 0.24714964840905831, "max": 0.3843904335802768, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19609053710512087, "min": 0.11743096349413926, "max": 0.2742423076986098, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7843621484204835, "min": 0.469723853976557, "max": 1.289528708831937, "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.Environment.CumulativeReward.mean": { "value": 25.181818181818183, "min": 3.1363636363636362, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 138.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.1363636363636362, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 138.0, "max": 1378.0, "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": "1679939099", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "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": "1679939622" }, "total": 523.337391701, "count": 1, "self": 0.8419446849999304, "children": { "run_training.setup": { "total": 0.1803332830000386, "count": 1, "self": 0.1803332830000386 }, "TrainerController.start_learning": { "total": 522.315113733, "count": 1, "self": 0.6819346729979543, "children": { "TrainerController._reset_env": { "total": 9.293987587999993, "count": 1, "self": 9.293987587999993 }, "TrainerController.advance": { "total": 512.105258727002, "count": 18222, "self": 0.33815786600086994, "children": { "env_step": { "total": 511.76710086100115, "count": 18222, "self": 370.3070932840057, "children": { "SubprocessEnvManager._take_step": { "total": 141.14105436699418, "count": 18222, "self": 2.5511634209974545, "children": { "TorchPolicy.evaluate": { "total": 138.58989094599673, "count": 18222, "self": 138.58989094599673 } } }, "workers": { "total": 0.3189532100012684, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 520.5711483179914, "count": 18222, "is_parallel": true, "self": 246.05900077799805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0069030290000000605, "count": 1, "is_parallel": true, "self": 0.004511496000020543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023915329999795176, "count": 10, "is_parallel": true, "self": 0.0023915329999795176 } } }, "UnityEnvironment.step": { "total": 0.05235226400003512, "count": 1, "is_parallel": true, "self": 0.00047178300002315154, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003095449999932498, "count": 1, "is_parallel": true, "self": 0.0003095449999932498 }, "communicator.exchange": { "total": 0.04987540199999785, "count": 1, "is_parallel": true, "self": 0.04987540199999785 }, "steps_from_proto": { "total": 0.0016955340000208707, "count": 1, "is_parallel": true, "self": 0.0003813500001115244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013141839999093463, "count": 10, "is_parallel": true, "self": 0.0013141839999093463 } } } } } } }, "UnityEnvironment.step": { "total": 274.51214753999335, "count": 18221, "is_parallel": true, "self": 10.901334580005539, "children": { "UnityEnvironment._generate_step_input": { "total": 5.962669892001088, "count": 18221, "is_parallel": true, "self": 5.962669892001088 }, "communicator.exchange": { "total": 221.08619323799525, "count": 18221, "is_parallel": true, "self": 221.08619323799525 }, "steps_from_proto": { "total": 36.56194982999148, "count": 18221, "is_parallel": true, "self": 7.516236065021133, "children": { "_process_rank_one_or_two_observation": { "total": 29.045713764970344, "count": 182210, "is_parallel": true, "self": 29.045713764970344 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015669999993406236, "count": 1, "self": 0.00015669999993406236, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 508.22050142001126, "count": 447437, "is_parallel": true, "self": 11.483790258038027, "children": { "process_trajectory": { "total": 283.7604445959734, "count": 447437, "is_parallel": true, "self": 281.9131805019734, "children": { "RLTrainer._checkpoint": { "total": 1.8472640940000247, "count": 4, "is_parallel": true, "self": 1.8472640940000247 } } }, "_update_policy": { "total": 212.97626656599982, "count": 90, "is_parallel": true, "self": 79.09837288599863, "children": { "TorchPPOOptimizer.update": { "total": 133.8778936800012, "count": 4581, "is_parallel": true, "self": 133.8778936800012 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23377604500001326, "count": 1, "self": 0.0012073009999085116, "children": { "RLTrainer._checkpoint": { "total": 0.23256874400010474, "count": 1, "self": 0.23256874400010474 } } } } } } }