{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9287739992141724, "min": 0.9280487895011902, "max": 2.8561530113220215, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8949.666015625, "min": 8949.666015625, "max": 29406.951171875, "count": 40 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.905447006225586, "min": 0.5786064863204956, "max": 12.905447006225586, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.562255859375, "min": 112.2496566772461, "max": 2621.890625, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06731770809539525, "min": 0.061492901207370144, "max": 0.07576727111140202, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.269270832381581, "min": 0.24846241197847835, "max": 0.35596822799119515, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21568000992285272, "min": 0.129375549238723, "max": 0.30613684589956325, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8627200396914109, "min": 0.517502196954892, "max": 1.5306842294978162, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.75, "min": 3.840909090909091, "max": 25.509090909090908, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1089.0, "min": 169.0, "max": 1403.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.75, "min": 3.840909090909091, "max": 25.509090909090908, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1089.0, "min": 169.0, "max": 1403.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678702181", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678702673" }, "total": 491.653605428, "count": 1, "self": 0.7467630479995933, "children": { "run_training.setup": { "total": 0.10854467600029238, "count": 1, "self": 0.10854467600029238 }, "TrainerController.start_learning": { "total": 490.7982977040001, "count": 1, "self": 0.5911668379853836, "children": { "TrainerController._reset_env": { "total": 9.397141920000195, "count": 1, "self": 9.397141920000195 }, "TrainerController.advance": { "total": 480.6183143090143, "count": 18222, "self": 0.29627380504780376, "children": { "env_step": { "total": 480.3220405039665, "count": 18222, "self": 340.9029274898867, "children": { "SubprocessEnvManager._take_step": { "total": 139.13937262406944, "count": 18222, "self": 1.8084356180693248, "children": { "TorchPolicy.evaluate": { "total": 137.3309370060001, "count": 18222, "self": 137.3309370060001 } } }, "workers": { "total": 0.27974039001037454, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 488.7129813820043, "count": 18222, "is_parallel": true, "self": 237.26808483400646, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002197125999828131, "count": 1, "is_parallel": true, "self": 0.0006360069996844686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015611190001436626, "count": 10, "is_parallel": true, "self": 0.0015611190001436626 } } }, "UnityEnvironment.step": { "total": 0.03862393500003236, "count": 1, "is_parallel": true, "self": 0.0004178619997219357, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004190720001133741, "count": 1, "is_parallel": true, "self": 0.0004190720001133741 }, "communicator.exchange": { "total": 0.035767889999988256, "count": 1, "is_parallel": true, "self": 0.035767889999988256 }, "steps_from_proto": { "total": 0.0020191110002087953, "count": 1, "is_parallel": true, "self": 0.00040259900106320856, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016165119991455867, "count": 10, "is_parallel": true, "self": 0.0016165119991455867 } } } } } } }, "UnityEnvironment.step": { "total": 251.4448965479978, "count": 18221, "is_parallel": true, "self": 9.8024580989686, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5174470640254185, "count": 18221, "is_parallel": true, "self": 5.5174470640254185 }, "communicator.exchange": { "total": 202.3508886659879, "count": 18221, "is_parallel": true, "self": 202.3508886659879 }, "steps_from_proto": { "total": 33.7741027190159, "count": 18221, "is_parallel": true, "self": 6.798198959953879, "children": { "_process_rank_one_or_two_observation": { "total": 26.97590375906202, "count": 182210, "is_parallel": true, "self": 26.97590375906202 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001260230001207674, "count": 1, "self": 0.0001260230001207674, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 476.74090072148874, "count": 434130, "is_parallel": true, "self": 10.992167388473263, "children": { "process_trajectory": { "total": 267.56611313401754, "count": 434130, "is_parallel": true, "self": 266.3250309080172, "children": { "RLTrainer._checkpoint": { "total": 1.2410822260003442, "count": 4, "is_parallel": true, "self": 1.2410822260003442 } } }, "_update_policy": { "total": 198.18262019899794, "count": 90, "is_parallel": true, "self": 77.6403090479971, "children": { "TorchPPOOptimizer.update": { "total": 120.54231115100083, "count": 4587, "is_parallel": true, "self": 120.54231115100083 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19154861400011214, "count": 1, "self": 0.0011356670001987368, "children": { "RLTrainer._checkpoint": { "total": 0.1904129469999134, "count": 1, "self": 0.1904129469999134 } } } } } } }