{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.05189847946167, "min": 1.05189847946167, "max": 2.8603594303131104, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10043.5263671875, "min": 10043.5263671875, "max": 29261.4765625, "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": 12.182308197021484, "min": 0.5505675673484802, "max": 12.182308197021484, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2375.550048828125, "min": 106.81011199951172, "max": 2443.697265625, "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": 0.06550403570444735, "min": 0.06331730670467996, "max": 0.07381194682184644, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2620161428177894, "min": 0.25326922681871983, "max": 0.3690597341092322, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21202589542258019, "min": 0.14088618809667727, "max": 0.26714248148834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8481035816903207, "min": 0.5635447523867091, "max": 1.3357124074417002, "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": 24.022727272727273, "min": 3.8636363636363638, "max": 24.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1057.0, "min": 170.0, "max": 1333.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.022727272727273, "min": 3.8636363636363638, "max": 24.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1057.0, "min": 170.0, "max": 1333.0, "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": "1709614232", "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": "1709614669" }, "total": 436.73759669599997, "count": 1, "self": 0.43722051799989003, "children": { "run_training.setup": { "total": 0.04811870900005033, "count": 1, "self": 0.04811870900005033 }, "TrainerController.start_learning": { "total": 436.252257469, "count": 1, "self": 0.5408459319974668, "children": { "TrainerController._reset_env": { "total": 3.229191286999992, "count": 1, "self": 3.229191286999992 }, "TrainerController.advance": { "total": 432.39351819700255, "count": 18198, "self": 0.26693060500309684, "children": { "env_step": { "total": 432.12658759199945, "count": 18198, "self": 279.2381697789968, "children": { "SubprocessEnvManager._take_step": { "total": 152.61870772900323, "count": 18198, "self": 1.417589052006349, "children": { "TorchPolicy.evaluate": { "total": 151.20111867699688, "count": 18198, "self": 151.20111867699688 } } }, "workers": { "total": 0.26971008399942775, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 435.05237840499916, "count": 18198, "is_parallel": true, "self": 216.54798908000686, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006248827000035817, "count": 1, "is_parallel": true, "self": 0.004547500000001037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017013270000347802, "count": 10, "is_parallel": true, "self": 0.0017013270000347802 } } }, "UnityEnvironment.step": { "total": 0.04858463800002255, "count": 1, "is_parallel": true, "self": 0.0007758310000554047, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047357500000089203, "count": 1, "is_parallel": true, "self": 0.00047357500000089203 }, "communicator.exchange": { "total": 0.045201052999971125, "count": 1, "is_parallel": true, "self": 0.045201052999971125 }, "steps_from_proto": { "total": 0.002134178999995129, "count": 1, "is_parallel": true, "self": 0.0005763990000673402, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015577799999277886, "count": 10, "is_parallel": true, "self": 0.0015577799999277886 } } } } } } }, "UnityEnvironment.step": { "total": 218.5043893249923, "count": 18197, "is_parallel": true, "self": 10.685936381995361, "children": { "UnityEnvironment._generate_step_input": { "total": 5.460175255007982, "count": 18197, "is_parallel": true, "self": 5.460175255007982 }, "communicator.exchange": { "total": 169.01210448299298, "count": 18197, "is_parallel": true, "self": 169.01210448299298 }, "steps_from_proto": { "total": 33.34617320499598, "count": 18197, "is_parallel": true, "self": 6.127497875007805, "children": { "_process_rank_one_or_two_observation": { "total": 27.218675329988173, "count": 181970, "is_parallel": true, "self": 27.218675329988173 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019330999998601328, "count": 1, "self": 0.00019330999998601328, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 426.91114073301827, "count": 669234, "is_parallel": true, "self": 13.874245147070098, "children": { "process_trajectory": { "total": 234.80925819894787, "count": 669234, "is_parallel": true, "self": 234.31098864394772, "children": { "RLTrainer._checkpoint": { "total": 0.49826955500014947, "count": 4, "is_parallel": true, "self": 0.49826955500014947 } } }, "_update_policy": { "total": 178.2276373870003, "count": 90, "is_parallel": true, "self": 52.08000323099742, "children": { "TorchPPOOptimizer.update": { "total": 126.14763415600288, "count": 4587, "is_parallel": true, "self": 126.14763415600288 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08850874300003397, "count": 1, "self": 0.000997207999944294, "children": { "RLTrainer._checkpoint": { "total": 0.08751153500008968, "count": 1, "self": 0.08751153500008968 } } } } } } }