{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0686928033828735, "min": 1.0686928033828735, "max": 2.8758785724639893, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10215.634765625, "min": 10215.634765625, "max": 29483.5078125, "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": 12.64936351776123, "min": 0.11045170575380325, "max": 12.64936351776123, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2466.6259765625, "min": 21.427631378173828, "max": 2542.639892578125, "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": 0.06363169292504323, "min": 0.06214011050826372, "max": 0.07633069431655767, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2545267717001729, "min": 0.2545267717001729, "max": 0.3816534715827884, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18989358418712432, "min": 0.10092394382523956, "max": 0.26019447480931, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7595743367484973, "min": 0.40369577530095824, "max": 1.3009723740465502, "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": 25.227272727272727, "min": 2.977272727272727, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 131.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 2.977272727272727, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 131.0, "max": 1375.0, "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": "1718940480", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718941115" }, "total": 635.346761347, "count": 1, "self": 0.5466048219998356, "children": { "run_training.setup": { "total": 0.12127208000015344, "count": 1, "self": 0.12127208000015344 }, "TrainerController.start_learning": { "total": 634.678884445, "count": 1, "self": 0.9179497259967775, "children": { "TrainerController._reset_env": { "total": 4.414748823000082, "count": 1, "self": 4.414748823000082 }, "TrainerController.advance": { "total": 629.231573079003, "count": 18203, "self": 0.4364150480162152, "children": { "env_step": { "total": 628.7951580309868, "count": 18203, "self": 484.07786277297555, "children": { "SubprocessEnvManager._take_step": { "total": 144.28219757501006, "count": 18203, "self": 2.6697458770036064, "children": { "TorchPolicy.evaluate": { "total": 141.61245169800645, "count": 18203, "self": 141.61245169800645 } } }, "workers": { "total": 0.4350976830012314, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 632.3740822440136, "count": 18203, "is_parallel": true, "self": 299.56222720701294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.01009385099996507, "count": 1, "is_parallel": true, "self": 0.007455068000354004, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026387829996110668, "count": 10, "is_parallel": true, "self": 0.0026387829996110668 } } }, "UnityEnvironment.step": { "total": 0.05034626599990588, "count": 1, "is_parallel": true, "self": 0.0008572609999646374, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004943809999531368, "count": 1, "is_parallel": true, "self": 0.0004943809999531368 }, "communicator.exchange": { "total": 0.04604309499995907, "count": 1, "is_parallel": true, "self": 0.04604309499995907 }, "steps_from_proto": { "total": 0.0029515290000290406, "count": 1, "is_parallel": true, "self": 0.0004849099998409656, "children": { "_process_rank_one_or_two_observation": { "total": 0.002466619000188075, "count": 10, "is_parallel": true, "self": 0.002466619000188075 } } } } } } }, "UnityEnvironment.step": { "total": 332.81185503700067, "count": 18202, "is_parallel": true, "self": 15.804328168025904, "children": { "UnityEnvironment._generate_step_input": { "total": 7.855756366988999, "count": 18202, "is_parallel": true, "self": 7.855756366988999 }, "communicator.exchange": { "total": 262.7569181199742, "count": 18202, "is_parallel": true, "self": 262.7569181199742 }, "steps_from_proto": { "total": 46.39485238201155, "count": 18202, "is_parallel": true, "self": 9.209002427059659, "children": { "_process_rank_one_or_two_observation": { "total": 37.18584995495189, "count": 182020, "is_parallel": true, "self": 37.18584995495189 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00026280999986738607, "count": 1, "self": 0.00026280999986738607, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 622.0125322621082, "count": 794170, "is_parallel": true, "self": 19.08472838404805, "children": { "process_trajectory": { "total": 335.07077925006024, "count": 794170, "is_parallel": true, "self": 334.32111755506, "children": { "RLTrainer._checkpoint": { "total": 0.7496616950002135, "count": 4, "is_parallel": true, "self": 0.7496616950002135 } } }, "_update_policy": { "total": 267.85702462799986, "count": 90, "is_parallel": true, "self": 73.73692957899948, "children": { "TorchPPOOptimizer.update": { "total": 194.12009504900038, "count": 4587, "is_parallel": true, "self": 194.12009504900038 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11435000700021192, "count": 1, "self": 0.0018209500003649737, "children": { "RLTrainer._checkpoint": { "total": 0.11252905699984694, "count": 1, "self": 0.11252905699984694 } } } } } } }