{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6599276661872864, "min": 0.6592596173286438, "max": 2.858964204788208, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6271.95263671875, "min": 6271.95263671875, "max": 29184.306640625, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.898180961608887, "min": 0.49817579984664917, "max": 11.90482234954834, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2308.2470703125, "min": 96.64610290527344, "max": 2439.81201171875, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07134531507572142, "min": 0.061597338263299224, "max": 0.07585763638952117, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2853812603028857, "min": 0.2463893530531969, "max": 0.35761168349327976, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1767628933942201, "min": 0.11776766857570586, "max": 0.29798037135133554, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7070515735768804, "min": 0.47107067430282346, "max": 1.282471615017629, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.7456980848e-06, "min": 5.7456980848e-06, "max": 0.0002935056021648, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.29827923392e-05, "min": 2.29827923392e-05, "max": 0.0014081280306239997, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191520000000001, "min": 0.10191520000000001, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40766080000000005, "min": 0.40766080000000005, "max": 0.9693760000000002, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000002, "min": 0.00010556848000000002, "max": 0.004891976480000001, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004222739200000001, "min": 0.0004222739200000001, "max": 0.023471862399999998, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.40909090909091, "min": 3.8636363636363638, "max": 23.681818181818183, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1030.0, "min": 170.0, "max": 1290.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.40909090909091, "min": 3.8636363636363638, "max": 23.681818181818183, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1030.0, "min": 170.0, "max": 1290.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1745567499", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745568169" }, "total": 669.6728046899999, "count": 1, "self": 0.5405483920000052, "children": { "run_training.setup": { "total": 0.029791821999992862, "count": 1, "self": 0.029791821999992862 }, "TrainerController.start_learning": { "total": 669.1024644759999, "count": 1, "self": 0.7102466549972632, "children": { "TrainerController._reset_env": { "total": 3.686585379999997, "count": 1, "self": 3.686585379999997 }, "TrainerController.advance": { "total": 664.6279680480026, "count": 22728, "self": 0.7523029120210367, "children": { "env_step": { "total": 466.29281076099574, "count": 22728, "self": 399.1241072780017, "children": { "SubprocessEnvManager._take_step": { "total": 66.721473580002, "count": 22728, "self": 2.334963637987812, "children": { "TorchPolicy.evaluate": { "total": 64.38650994201419, "count": 22728, "self": 64.38650994201419 } } }, "workers": { "total": 0.447229902992035, "count": 22728, "self": 0.0, "children": { "worker_root": { "total": 666.5097830869889, "count": 22728, "is_parallel": true, "self": 321.0084219539714, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006054275999986203, "count": 1, "is_parallel": true, "self": 0.00430584799994449, "children": { "_process_rank_one_or_two_observation": { "total": 0.001748428000041713, "count": 10, "is_parallel": true, "self": 0.001748428000041713 } } }, "UnityEnvironment.step": { "total": 0.07888650300003519, "count": 1, "is_parallel": true, "self": 0.0007583489999660742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004408790000525187, "count": 1, "is_parallel": true, "self": 0.0004408790000525187 }, "communicator.exchange": { "total": 0.07038866499999585, "count": 1, "is_parallel": true, "self": 0.07038866499999585 }, "steps_from_proto": { "total": 0.007298610000020744, "count": 1, "is_parallel": true, "self": 0.0004917170000453552, "children": { "_process_rank_one_or_two_observation": { "total": 0.006806892999975389, "count": 10, "is_parallel": true, "self": 0.006806892999975389 } } } } } } }, "UnityEnvironment.step": { "total": 345.50136113301755, "count": 22727, "is_parallel": true, "self": 17.009702824995657, "children": { "UnityEnvironment._generate_step_input": { "total": 9.016643998002905, "count": 22727, "is_parallel": true, "self": 9.016643998002905 }, "communicator.exchange": { "total": 268.75805613600926, "count": 22727, "is_parallel": true, "self": 268.75805613600926 }, "steps_from_proto": { "total": 50.71695817400973, "count": 22727, "is_parallel": true, "self": 9.746280386986427, "children": { "_process_rank_one_or_two_observation": { "total": 40.970677787023305, "count": 227270, "is_parallel": true, "self": 40.970677787023305 } } } } } } } } } } }, "trainer_advance": { "total": 197.5828543749858, "count": 22728, "self": 1.002548161979803, "children": { "process_trajectory": { "total": 37.41682645900585, "count": 22728, "self": 36.35437363100607, "children": { "RLTrainer._checkpoint": { "total": 1.0624528279997776, "count": 10, "self": 1.0624528279997776 } } }, "_update_policy": { "total": 159.16347975400015, "count": 113, "self": 60.95975911199662, "children": { "TorchPPOOptimizer.update": { "total": 98.20372064200353, "count": 5760, "self": 98.20372064200353 } } } } } } }, "trainer_threads": { "total": 1.005000058285077e-06, "count": 1, "self": 1.005000058285077e-06 }, "TrainerController._save_models": { "total": 0.07766338800001904, "count": 1, "self": 0.0010960399999930814, "children": { "RLTrainer._checkpoint": { "total": 0.07656734800002596, "count": 1, "self": 0.07656734800002596 } } } } } } }