{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0101943016052246, "min": 1.0101943016052246, "max": 2.839812994003296, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9645.3349609375, "min": 9645.3349609375, "max": 29269.953125, "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": 11.793662071228027, "min": 0.25998616218566895, "max": 11.810311317443848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2299.76416015625, "min": 50.43731689453125, "max": 2409.303466796875, "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": 0.07223837455254112, "min": 0.062364808355271764, "max": 0.07469677052946352, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28895349821016447, "min": 0.25223274173913524, "max": 0.3631257636713118, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20370641891278474, "min": 0.11659122642367055, "max": 0.2686379820108414, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.814825675651139, "min": 0.4663649056946822, "max": 1.3431899100542068, "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": 22.5, "min": 3.227272727272727, "max": 23.4, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 990.0, "min": 142.0, "max": 1287.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.5, "min": 3.227272727272727, "max": 23.4, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 990.0, "min": 142.0, "max": 1287.0, "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": "1724939431", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1v2 --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1724939974" }, "total": 543.5991986669999, "count": 1, "self": 0.47785627600001135, "children": { "run_training.setup": { "total": 0.054553988999941794, "count": 1, "self": 0.054553988999941794 }, "TrainerController.start_learning": { "total": 543.0667884019999, "count": 1, "self": 0.7619434519945116, "children": { "TrainerController._reset_env": { "total": 2.189774151999927, "count": 1, "self": 2.189774151999927 }, "TrainerController.advance": { "total": 540.0193874870056, "count": 18201, "self": 0.3617795149887115, "children": { "env_step": { "total": 539.6576079720169, "count": 18201, "self": 352.7570594860017, "children": { "SubprocessEnvManager._take_step": { "total": 186.5166578969986, "count": 18201, "self": 1.8277789890200893, "children": { "TorchPolicy.evaluate": { "total": 184.6888789079785, "count": 18201, "self": 184.6888789079785 } } }, "workers": { "total": 0.38389058901657336, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 541.3840490399941, "count": 18201, "is_parallel": true, "self": 265.6341495700058, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025089739999657468, "count": 1, "is_parallel": true, "self": 0.0008173450003141625, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016916289996515843, "count": 10, "is_parallel": true, "self": 0.0016916289996515843 } } }, "UnityEnvironment.step": { "total": 0.04095943800007262, "count": 1, "is_parallel": true, "self": 0.0006672340000477561, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004918080001061753, "count": 1, "is_parallel": true, "self": 0.0004918080001061753 }, "communicator.exchange": { "total": 0.037323893999882785, "count": 1, "is_parallel": true, "self": 0.037323893999882785 }, "steps_from_proto": { "total": 0.0024765020000359073, "count": 1, "is_parallel": true, "self": 0.0004399499998726242, "children": { "_process_rank_one_or_two_observation": { "total": 0.002036552000163283, "count": 10, "is_parallel": true, "self": 0.002036552000163283 } } } } } } }, "UnityEnvironment.step": { "total": 275.74989946998835, "count": 18200, "is_parallel": true, "self": 12.180957115959018, "children": { "UnityEnvironment._generate_step_input": { "total": 6.594429396015357, "count": 18200, "is_parallel": true, "self": 6.594429396015357 }, "communicator.exchange": { "total": 211.94975153501014, "count": 18200, "is_parallel": true, "self": 211.94975153501014 }, "steps_from_proto": { "total": 45.02476142300384, "count": 18200, "is_parallel": true, "self": 8.377023530966653, "children": { "_process_rank_one_or_two_observation": { "total": 36.647737892037185, "count": 182000, "is_parallel": true, "self": 36.647737892037185 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013666499989994918, "count": 1, "self": 0.00013666499989994918, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 533.394791664952, "count": 806319, "is_parallel": true, "self": 17.17544031684156, "children": { "process_trajectory": { "total": 291.53462325311034, "count": 806319, "is_parallel": true, "self": 290.83716802711024, "children": { "RLTrainer._checkpoint": { "total": 0.6974552260001019, "count": 4, "is_parallel": true, "self": 0.6974552260001019 } } }, "_update_policy": { "total": 224.68472809500008, "count": 90, "is_parallel": true, "self": 77.74309676400003, "children": { "TorchPPOOptimizer.update": { "total": 146.94163133100005, "count": 4584, "is_parallel": true, "self": 146.94163133100005 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09554664600000251, "count": 1, "self": 0.0009135520001564146, "children": { "RLTrainer._checkpoint": { "total": 0.0946330939998461, "count": 1, "self": 0.0946330939998461 } } } } } } }