{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6903461217880249, "min": 0.6903461217880249, "max": 2.853588342666626, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6561.0498046875, "min": 6561.0498046875, "max": 29129.4296875, "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": 13.038019180297852, "min": 0.37644249200820923, "max": 13.157166481018066, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2542.413818359375, "min": 73.02984619140625, "max": 2675.38134765625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06244533171506565, "min": 0.06244533171506565, "max": 0.07701724110965563, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2497813268602626, "min": 0.2497813268602626, "max": 0.3677751860060894, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21047926372757145, "min": 0.11624345265433886, "max": 0.28869979755551206, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8419170549102858, "min": 0.46497381061735543, "max": 1.4434989877775604, "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.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.Environment.CumulativeReward.mean": { "value": 25.272727272727273, "min": 3.5454545454545454, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 156.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.5454545454545454, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 156.0, "max": 1398.0, "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": "1767017087", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767017508" }, "total": 420.8341608989999, "count": 1, "self": 0.4361494969998603, "children": { "run_training.setup": { "total": 0.02819801199984795, "count": 1, "self": 0.02819801199984795 }, "TrainerController.start_learning": { "total": 420.3698133900002, "count": 1, "self": 0.34617002796176166, "children": { "TrainerController._reset_env": { "total": 2.9478991839996525, "count": 1, "self": 2.9478991839996525 }, "TrainerController.advance": { "total": 417.0023767840389, "count": 18192, "self": 0.37573887603730327, "children": { "env_step": { "total": 300.18203693201167, "count": 18192, "self": 234.9273009300341, "children": { "SubprocessEnvManager._take_step": { "total": 65.05746484898555, "count": 18192, "self": 1.1784453790160114, "children": { "TorchPolicy.evaluate": { "total": 63.879019469969535, "count": 18192, "self": 63.879019469969535 } } }, "workers": { "total": 0.19727115299201614, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 418.5144821209915, "count": 18192, "is_parallel": true, "self": 212.0131174440071, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004902556999695662, "count": 1, "is_parallel": true, "self": 0.0034515140000621614, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014510429996335006, "count": 10, "is_parallel": true, "self": 0.0014510429996335006 } } }, "UnityEnvironment.step": { "total": 0.03488350600036938, "count": 1, "is_parallel": true, "self": 0.0005644700008815562, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046223100025599706, "count": 1, "is_parallel": true, "self": 0.00046223100025599706 }, "communicator.exchange": { "total": 0.032040554999639426, "count": 1, "is_parallel": true, "self": 0.032040554999639426 }, "steps_from_proto": { "total": 0.0018162499995924009, "count": 1, "is_parallel": true, "self": 0.00034203099994556396, "children": { "_process_rank_one_or_two_observation": { "total": 0.001474218999646837, "count": 10, "is_parallel": true, "self": 0.001474218999646837 } } } } } } }, "UnityEnvironment.step": { "total": 206.5013646769844, "count": 18191, "is_parallel": true, "self": 9.866139740019662, "children": { "UnityEnvironment._generate_step_input": { "total": 5.249625954978455, "count": 18191, "is_parallel": true, "self": 5.249625954978455 }, "communicator.exchange": { "total": 157.10476693999135, "count": 18191, "is_parallel": true, "self": 157.10476693999135 }, "steps_from_proto": { "total": 34.28083204199493, "count": 18191, "is_parallel": true, "self": 6.281105842977013, "children": { "_process_rank_one_or_two_observation": { "total": 27.999726199017914, "count": 181910, "is_parallel": true, "self": 27.999726199017914 } } } } } } } } } } }, "trainer_advance": { "total": 116.44460097598994, "count": 18192, "self": 0.42658308597356154, "children": { "process_trajectory": { "total": 25.160212503014463, "count": 18192, "self": 24.655751828014218, "children": { "RLTrainer._checkpoint": { "total": 0.5044606750002458, "count": 4, "self": 0.5044606750002458 } } }, "_update_policy": { "total": 90.85780538700192, "count": 90, "self": 37.37884805699741, "children": { "TorchPPOOptimizer.update": { "total": 53.478957330004505, "count": 4587, "self": 53.478957330004505 } } } } } } }, "trainer_threads": { "total": 8.659999366500415e-07, "count": 1, "self": 8.659999366500415e-07 }, "TrainerController._save_models": { "total": 0.07336652799995136, "count": 1, "self": 0.0006826819999332656, "children": { "RLTrainer._checkpoint": { "total": 0.07268384600001809, "count": 1, "self": 0.07268384600001809 } } } } } } }