{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1091419458389282, "min": 1.1091419458389282, "max": 2.859332323074341, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10577.88671875, "min": 10577.88671875, "max": 29250.96875, "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": 11.770546913146973, "min": 0.5992348790168762, "max": 11.818026542663574, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2295.256591796875, "min": 116.2515640258789, "max": 2410.87744140625, "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": 0.0675990958453422, "min": 0.06058719394076095, "max": 0.0723427370653999, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2703963833813688, "min": 0.2423487757630438, "max": 0.3594590989355222, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20298730355559613, "min": 0.14057871995165067, "max": 0.27051054449642403, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8119492142223845, "min": 0.5623148798066027, "max": 1.35255272248212, "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": 23.227272727272727, "min": 4.181818181818182, "max": 23.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1022.0, "min": 184.0, "max": 1268.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.227272727272727, "min": 4.181818181818182, "max": 23.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1022.0, "min": 184.0, "max": 1268.0, "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": "1706255852", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706256319" }, "total": 466.496157879, "count": 1, "self": 0.4354713200000333, "children": { "run_training.setup": { "total": 0.05219686200001661, "count": 1, "self": 0.05219686200001661 }, "TrainerController.start_learning": { "total": 466.00848969699996, "count": 1, "self": 0.6780830850021289, "children": { "TrainerController._reset_env": { "total": 3.1944233479999866, "count": 1, "self": 3.1944233479999866 }, "TrainerController.advance": { "total": 462.0375305519978, "count": 18198, "self": 0.34571112499310175, "children": { "env_step": { "total": 461.6918194270047, "count": 18198, "self": 302.84301284900295, "children": { "SubprocessEnvManager._take_step": { "total": 158.51699837999752, "count": 18198, "self": 1.5969971889945214, "children": { "TorchPolicy.evaluate": { "total": 156.920001191003, "count": 18198, "self": 156.920001191003 } } }, "workers": { "total": 0.33180819800423933, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 464.6121231970025, "count": 18198, "is_parallel": true, "self": 225.15914392500287, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004267322000032436, "count": 1, "is_parallel": true, "self": 0.0029151209999440653, "children": { "_process_rank_one_or_two_observation": { "total": 0.001352201000088371, "count": 10, "is_parallel": true, "self": 0.001352201000088371 } } }, "UnityEnvironment.step": { "total": 0.037913336999963576, "count": 1, "is_parallel": true, "self": 0.0007681700000148339, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041018599995368277, "count": 1, "is_parallel": true, "self": 0.00041018599995368277 }, "communicator.exchange": { "total": 0.03465528300000642, "count": 1, "is_parallel": true, "self": 0.03465528300000642 }, "steps_from_proto": { "total": 0.002079697999988639, "count": 1, "is_parallel": true, "self": 0.0003823829999305417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016973150000580972, "count": 10, "is_parallel": true, "self": 0.0016973150000580972 } } } } } } }, "UnityEnvironment.step": { "total": 239.45297927199965, "count": 18197, "is_parallel": true, "self": 11.47456875100346, "children": { "UnityEnvironment._generate_step_input": { "total": 5.742152487998624, "count": 18197, "is_parallel": true, "self": 5.742152487998624 }, "communicator.exchange": { "total": 187.17348294000027, "count": 18197, "is_parallel": true, "self": 187.17348294000027 }, "steps_from_proto": { "total": 35.0627750929973, "count": 18197, "is_parallel": true, "self": 6.957463448967928, "children": { "_process_rank_one_or_two_observation": { "total": 28.10531164402937, "count": 181970, "is_parallel": true, "self": 28.10531164402937 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019434800003637065, "count": 1, "self": 0.00019434800003637065, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.344831167062, "count": 731550, "is_parallel": true, "self": 14.877868361088474, "children": { "process_trajectory": { "total": 253.3843390189735, "count": 731550, "is_parallel": true, "self": 252.42949356997337, "children": { "RLTrainer._checkpoint": { "total": 0.9548454490001177, "count": 4, "is_parallel": true, "self": 0.9548454490001177 } } }, "_update_policy": { "total": 188.08262378700005, "count": 90, "is_parallel": true, "self": 52.40702402999921, "children": { "TorchPPOOptimizer.update": { "total": 135.67559975700084, "count": 4584, "is_parallel": true, "self": 135.67559975700084 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09825836400000298, "count": 1, "self": 0.001099095999961719, "children": { "RLTrainer._checkpoint": { "total": 0.09715926800004127, "count": 1, "self": 0.09715926800004127 } } } } } } }