{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7498764395713806, "min": 0.7498764395713806, "max": 2.853954792022705, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7126.82568359375, "min": 7126.82568359375, "max": 29133.169921875, "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": 13.129326820373535, "min": 0.21694935858249664, "max": 13.302552223205566, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2547.08935546875, "min": 42.08817672729492, "max": 2713.720703125, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06237361735796131, "min": 0.06102633918549948, "max": 0.076506828447272, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24949446943184525, "min": 0.24410535674199793, "max": 0.38087669455340156, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15757101412643404, "min": 0.09607985840343378, "max": 0.2495065285879023, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6302840565057362, "min": 0.3843194336137351, "max": 1.2475326429395115, "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": 25.65909090909091, "min": 3.7045454545454546, "max": 26.09090909090909, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 163.0, "max": 1435.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 3.7045454545454546, "max": 26.09090909090909, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 163.0, "max": 1435.0, "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": "1769894145", "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": "1769894671" }, "total": 525.4305488040001, "count": 1, "self": 0.43517932300017037, "children": { "run_training.setup": { "total": 0.026357548999953906, "count": 1, "self": 0.026357548999953906 }, "TrainerController.start_learning": { "total": 524.969011932, "count": 1, "self": 0.4063689640138364, "children": { "TrainerController._reset_env": { "total": 2.943450650999921, "count": 1, "self": 2.943450650999921 }, "TrainerController.advance": { "total": 521.545380152986, "count": 22728, "self": 0.4219052990054024, "children": { "env_step": { "total": 375.5976816529925, "count": 22728, "self": 294.5825825719918, "children": { "SubprocessEnvManager._take_step": { "total": 80.7671016880114, "count": 22728, "self": 1.460853781005767, "children": { "TorchPolicy.evaluate": { "total": 79.30624790700563, "count": 22728, "self": 79.30624790700563 } } }, "workers": { "total": 0.2479973929893049, "count": 22728, "self": 0.0, "children": { "worker_root": { "total": 522.802646034005, "count": 22728, "is_parallel": true, "self": 263.63541238800747, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005017296999994869, "count": 1, "is_parallel": true, "self": 0.0036315639999884297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013857330000064394, "count": 10, "is_parallel": true, "self": 0.0013857330000064394 } } }, "UnityEnvironment.step": { "total": 0.0364463920000162, "count": 1, "is_parallel": true, "self": 0.0005731820000391963, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038880099998550577, "count": 1, "is_parallel": true, "self": 0.00038880099998550577 }, "communicator.exchange": { "total": 0.03368637799997032, "count": 1, "is_parallel": true, "self": 0.03368637799997032 }, "steps_from_proto": { "total": 0.001798031000021183, "count": 1, "is_parallel": true, "self": 0.0003431369999589151, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014548940000622679, "count": 10, "is_parallel": true, "self": 0.0014548940000622679 } } } } } } }, "UnityEnvironment.step": { "total": 259.1672336459975, "count": 22727, "is_parallel": true, "self": 12.50310607400661, "children": { "UnityEnvironment._generate_step_input": { "total": 6.524809306989027, "count": 22727, "is_parallel": true, "self": 6.524809306989027 }, "communicator.exchange": { "total": 197.82578640198744, "count": 22727, "is_parallel": true, "self": 197.82578640198744 }, "steps_from_proto": { "total": 42.31353186301442, "count": 22727, "is_parallel": true, "self": 7.6822490900301545, "children": { "_process_rank_one_or_two_observation": { "total": 34.631282772984264, "count": 227270, "is_parallel": true, "self": 34.631282772984264 } } } } } } } } } } }, "trainer_advance": { "total": 145.52579320098812, "count": 22728, "self": 0.5145760540027595, "children": { "process_trajectory": { "total": 30.967017710985942, "count": 22728, "self": 30.40582623298576, "children": { "RLTrainer._checkpoint": { "total": 0.5611914780001825, "count": 5, "self": 0.5611914780001825 } } }, "_update_policy": { "total": 114.04419943599942, "count": 113, "self": 47.25833948199977, "children": { "TorchPPOOptimizer.update": { "total": 66.78585995399965, "count": 5760, "self": 66.78585995399965 } } } } } } }, "trainer_threads": { "total": 1.0220001058769412e-06, "count": 1, "self": 1.0220001058769412e-06 }, "TrainerController._save_models": { "total": 0.07381114200006778, "count": 1, "self": 0.0006677950002540456, "children": { "RLTrainer._checkpoint": { "total": 0.07314334699981373, "count": 1, "self": 0.07314334699981373 } } } } } } }