{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9826645851135254, "min": 0.9595472812652588, "max": 2.876051425933838, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9382.4814453125, "min": 9382.4814453125, "max": 29485.279296875, "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": 12.686287879943848, "min": 0.17321273684501648, "max": 12.686287879943848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2473.826171875, "min": 33.603271484375, "max": 2548.7041015625, "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": 0.06781183155002438, "min": 0.05833585254236716, "max": 0.07383935839541522, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2712473262000975, "min": 0.23334341016946863, "max": 0.3691967919770761, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21530026219346943, "min": 0.12105725947813151, "max": 0.2775724879082512, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8612010487738777, "min": 0.48422903791252603, "max": 1.3878624395412558, "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": 25.0, "min": 3.1136363636363638, "max": 25.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 137.0, "max": 1368.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.1136363636363638, "max": 25.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 137.0, "max": 1368.0, "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": "1698029836", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698030418" }, "total": 581.3569084760002, "count": 1, "self": 0.6511489000001802, "children": { "run_training.setup": { "total": 0.067788506999932, "count": 1, "self": 0.067788506999932 }, "TrainerController.start_learning": { "total": 580.6379710690001, "count": 1, "self": 0.8339720600149576, "children": { "TrainerController._reset_env": { "total": 1.3356671830001687, "count": 1, "self": 1.3356671830001687 }, "TrainerController.advance": { "total": 578.3670032499851, "count": 18199, "self": 0.42754700999671513, "children": { "env_step": { "total": 577.9394562399884, "count": 18199, "self": 452.92919157501683, "children": { "SubprocessEnvManager._take_step": { "total": 124.59385108199763, "count": 18199, "self": 2.332601910009089, "children": { "TorchPolicy.evaluate": { "total": 122.26124917198854, "count": 18199, "self": 122.26124917198854 } } }, "workers": { "total": 0.41641358297397346, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 578.3774602329904, "count": 18199, "is_parallel": true, "self": 265.1466454149795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00240380299987919, "count": 1, "is_parallel": true, "self": 0.0007199520005087834, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016838509993704065, "count": 10, "is_parallel": true, "self": 0.0016838509993704065 } } }, "UnityEnvironment.step": { "total": 0.04180408199999874, "count": 1, "is_parallel": true, "self": 0.0007229479999750765, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036150000005363836, "count": 1, "is_parallel": true, "self": 0.00036150000005363836 }, "communicator.exchange": { "total": 0.03849074000004293, "count": 1, "is_parallel": true, "self": 0.03849074000004293 }, "steps_from_proto": { "total": 0.002228893999927095, "count": 1, "is_parallel": true, "self": 0.00044284699970376096, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017860470002233342, "count": 10, "is_parallel": true, "self": 0.0017860470002233342 } } } } } } }, "UnityEnvironment.step": { "total": 313.2308148180109, "count": 18198, "is_parallel": true, "self": 13.952097611960653, "children": { "UnityEnvironment._generate_step_input": { "total": 7.317864238017364, "count": 18198, "is_parallel": true, "self": 7.317864238017364 }, "communicator.exchange": { "total": 247.91398693002247, "count": 18198, "is_parallel": true, "self": 247.91398693002247 }, "steps_from_proto": { "total": 44.04686603801042, "count": 18198, "is_parallel": true, "self": 8.76862861100608, "children": { "_process_rank_one_or_two_observation": { "total": 35.27823742700434, "count": 181980, "is_parallel": true, "self": 35.27823742700434 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016588599987699126, "count": 1, "self": 0.00016588599987699126, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 573.2211687800841, "count": 582723, "is_parallel": true, "self": 13.81191701313196, "children": { "process_trajectory": { "total": 313.50409137795236, "count": 582723, "is_parallel": true, "self": 312.8928736509524, "children": { "RLTrainer._checkpoint": { "total": 0.6112177269999393, "count": 4, "is_parallel": true, "self": 0.6112177269999393 } } }, "_update_policy": { "total": 245.90516038899978, "count": 90, "is_parallel": true, "self": 70.69576776400004, "children": { "TorchPPOOptimizer.update": { "total": 175.20939262499974, "count": 4587, "is_parallel": true, "self": 175.20939262499974 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10116268999991007, "count": 1, "self": 0.002031100999829505, "children": { "RLTrainer._checkpoint": { "total": 0.09913158900008057, "count": 1, "self": 0.09913158900008057 } } } } } } }