{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9581717848777771, "min": 0.9581717848777771, "max": 2.847144842147827, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9148.6240234375, "min": 9148.6240234375, "max": 29157.609375, "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": 12.765079498291016, "min": 0.38392600417137146, "max": 12.774946212768555, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2489.1904296875, "min": 74.48164367675781, "max": 2615.978271484375, "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": 0.0675056985138665, "min": 0.06276176536881466, "max": 0.07291968387480843, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.270022794055466, "min": 0.25647137918813134, "max": 0.3645984193740422, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19889917991617148, "min": 0.11331411727530627, "max": 0.27202396042206706, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7955967196646859, "min": 0.4532564691012251, "max": 1.3601198021103353, "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": 25.15909090909091, "min": 3.522727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 155.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.522727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 155.0, "max": 1390.0, "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": "1713839258", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713839695" }, "total": 437.10931200899995, "count": 1, "self": 0.4314513399997395, "children": { "run_training.setup": { "total": 0.0548521250000249, "count": 1, "self": 0.0548521250000249 }, "TrainerController.start_learning": { "total": 436.6230085440002, "count": 1, "self": 0.5277147269966918, "children": { "TrainerController._reset_env": { "total": 2.911368141000139, "count": 1, "self": 2.911368141000139 }, "TrainerController.advance": { "total": 433.09435452500315, "count": 18199, "self": 0.25126676898298683, "children": { "env_step": { "total": 432.84308775602017, "count": 18199, "self": 279.50572807302115, "children": { "SubprocessEnvManager._take_step": { "total": 153.07000917300002, "count": 18199, "self": 1.441245732007701, "children": { "TorchPolicy.evaluate": { "total": 151.62876344099232, "count": 18199, "self": 151.62876344099232 } } }, "workers": { "total": 0.2673505099990052, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 435.49632950800765, "count": 18199, "is_parallel": true, "self": 218.8808741519897, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005353835000050822, "count": 1, "is_parallel": true, "self": 0.003656445000160602, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016973899998902198, "count": 10, "is_parallel": true, "self": 0.0016973899998902198 } } }, "UnityEnvironment.step": { "total": 0.037478368999927625, "count": 1, "is_parallel": true, "self": 0.0007036819999939325, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036504800004877325, "count": 1, "is_parallel": true, "self": 0.00036504800004877325 }, "communicator.exchange": { "total": 0.0344131849999485, "count": 1, "is_parallel": true, "self": 0.0344131849999485 }, "steps_from_proto": { "total": 0.0019964539999364206, "count": 1, "is_parallel": true, "self": 0.00038590899976043147, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016105450001759891, "count": 10, "is_parallel": true, "self": 0.0016105450001759891 } } } } } } }, "UnityEnvironment.step": { "total": 216.61545535601795, "count": 18198, "is_parallel": true, "self": 10.05808235404129, "children": { "UnityEnvironment._generate_step_input": { "total": 5.137277609987677, "count": 18198, "is_parallel": true, "self": 5.137277609987677 }, "communicator.exchange": { "total": 168.56490877800934, "count": 18198, "is_parallel": true, "self": 168.56490877800934 }, "steps_from_proto": { "total": 32.85518661397964, "count": 18198, "is_parallel": true, "self": 6.144076977944451, "children": { "_process_rank_one_or_two_observation": { "total": 26.71110963603519, "count": 181980, "is_parallel": true, "self": 26.71110963603519 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011125600008199399, "count": 1, "self": 0.00011125600008199399, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 427.98552456804964, "count": 631579, "is_parallel": true, "self": 13.402795108946066, "children": { "process_trajectory": { "total": 237.67139597410278, "count": 631579, "is_parallel": true, "self": 237.07190810610314, "children": { "RLTrainer._checkpoint": { "total": 0.5994878679996418, "count": 4, "is_parallel": true, "self": 0.5994878679996418 } } }, "_update_policy": { "total": 176.9113334850008, "count": 90, "is_parallel": true, "self": 51.17287915101406, "children": { "TorchPPOOptimizer.update": { "total": 125.73845433398674, "count": 4587, "is_parallel": true, "self": 125.73845433398674 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0894598950001182, "count": 1, "self": 0.0009335600002486899, "children": { "RLTrainer._checkpoint": { "total": 0.0885263349998695, "count": 1, "self": 0.0885263349998695 } } } } } } }