{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8479132652282715, "min": 0.8479132652282715, "max": 2.8319900035858154, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8058.56787109375, "min": 8058.56787109375, "max": 28908.953125, "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": 13.232016563415527, "min": 0.4742441475391388, "max": 13.232016563415527, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2580.2431640625, "min": 92.00336456298828, "max": 2683.29345703125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07374149580833796, "min": 0.060572946492888434, "max": 0.07552109497862379, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2949659832333518, "min": 0.2581107045624259, "max": 0.37109237298478975, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1928321170602359, "min": 0.13382277380579205, "max": 0.285136809536055, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7713284682409436, "min": 0.5352910952231682, "max": 1.4036046032812082, "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": 26.136363636363637, "min": 3.727272727272727, "max": 26.21818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1150.0, "min": 164.0, "max": 1442.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.136363636363637, "min": 3.727272727272727, "max": 26.21818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1150.0, "min": 164.0, "max": 1442.0, "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": "1743537027", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743537464" }, "total": 437.11586987299995, "count": 1, "self": 0.4390070970000579, "children": { "run_training.setup": { "total": 0.02328872699990825, "count": 1, "self": 0.02328872699990825 }, "TrainerController.start_learning": { "total": 436.653574049, "count": 1, "self": 0.3579047400080526, "children": { "TrainerController._reset_env": { "total": 2.9091712909998932, "count": 1, "self": 2.9091712909998932 }, "TrainerController.advance": { "total": 433.287021551992, "count": 18192, "self": 0.3754895749922298, "children": { "env_step": { "total": 307.21612133000315, "count": 18192, "self": 232.79164521999417, "children": { "SubprocessEnvManager._take_step": { "total": 74.21126375000881, "count": 18192, "self": 1.317365261015766, "children": { "TorchPolicy.evaluate": { "total": 72.89389848899305, "count": 18192, "self": 72.89389848899305 } } }, "workers": { "total": 0.21321236000017052, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 435.12531953000894, "count": 18192, "is_parallel": true, "self": 230.83433522501116, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005378631999974459, "count": 1, "is_parallel": true, "self": 0.003651430999980221, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017272009999942384, "count": 10, "is_parallel": true, "self": 0.0017272009999942384 } } }, "UnityEnvironment.step": { "total": 0.036222841999915545, "count": 1, "is_parallel": true, "self": 0.0005557169998837708, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003852349999533544, "count": 1, "is_parallel": true, "self": 0.0003852349999533544 }, "communicator.exchange": { "total": 0.03326324600004682, "count": 1, "is_parallel": true, "self": 0.03326324600004682 }, "steps_from_proto": { "total": 0.0020186440000315997, "count": 1, "is_parallel": true, "self": 0.0003897010001310264, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016289429999005733, "count": 10, "is_parallel": true, "self": 0.0016289429999005733 } } } } } } }, "UnityEnvironment.step": { "total": 204.29098430499778, "count": 18191, "is_parallel": true, "self": 9.702392309998686, "children": { "UnityEnvironment._generate_step_input": { "total": 5.470796979000056, "count": 18191, "is_parallel": true, "self": 5.470796979000056 }, "communicator.exchange": { "total": 156.85824171999786, "count": 18191, "is_parallel": true, "self": 156.85824171999786 }, "steps_from_proto": { "total": 32.25955329600117, "count": 18191, "is_parallel": true, "self": 5.74668869701884, "children": { "_process_rank_one_or_two_observation": { "total": 26.512864598982333, "count": 181910, "is_parallel": true, "self": 26.512864598982333 } } } } } } } } } } }, "trainer_advance": { "total": 125.6954106469966, "count": 18192, "self": 0.4396168850025788, "children": { "process_trajectory": { "total": 28.21431341699406, "count": 18192, "self": 27.558938122993936, "children": { "RLTrainer._checkpoint": { "total": 0.6553752940001232, "count": 4, "self": 0.6553752940001232 } } }, "_update_policy": { "total": 97.04148034499997, "count": 90, "self": 38.77258006599607, "children": { "TorchPPOOptimizer.update": { "total": 58.2689002790039, "count": 4587, "self": 58.2689002790039 } } } } } } }, "trainer_threads": { "total": 1.0230000953015406e-06, "count": 1, "self": 1.0230000953015406e-06 }, "TrainerController._save_models": { "total": 0.09947544299996025, "count": 1, "self": 0.0009420270000646269, "children": { "RLTrainer._checkpoint": { "total": 0.09853341599989562, "count": 1, "self": 0.09853341599989562 } } } } } } }