{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0338467359542847, "min": 1.0160326957702637, "max": 2.8572235107421875, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9905.28515625, "min": 9905.28515625, "max": 29292.255859375, "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": 11.806385040283203, "min": 0.32274389266967773, "max": 11.806385040283203, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2302.2451171875, "min": 62.61231231689453, "max": 2368.46728515625, "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": 0.06861308827815353, "min": 0.06118514080022293, "max": 0.07568165601759592, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2744523531126141, "min": 0.24577625403317677, "max": 0.3784082800879796, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21262627935000494, "min": 0.13789123504687395, "max": 0.3039626398069017, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8505051174000198, "min": 0.5515649401874958, "max": 1.4779579902396485, "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": 23.113636363636363, "min": 3.840909090909091, "max": 23.145454545454545, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1017.0, "min": 169.0, "max": 1273.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.113636363636363, "min": 3.840909090909091, "max": 23.145454545454545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1017.0, "min": 169.0, "max": 1273.0, "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": "1701814222", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701814847" }, "total": 625.688546077, "count": 1, "self": 0.7010774909998645, "children": { "run_training.setup": { "total": 0.06500037000000702, "count": 1, "self": 0.06500037000000702 }, "TrainerController.start_learning": { "total": 624.9224682160001, "count": 1, "self": 0.9232207719983307, "children": { "TrainerController._reset_env": { "total": 4.0884522869999955, "count": 1, "self": 4.0884522869999955 }, "TrainerController.advance": { "total": 619.8116455010017, "count": 18202, "self": 0.43739663400481277, "children": { "env_step": { "total": 619.3742488669969, "count": 18202, "self": 483.63479861401754, "children": { "SubprocessEnvManager._take_step": { "total": 135.2998292879854, "count": 18202, "self": 2.5824210019846987, "children": { "TorchPolicy.evaluate": { "total": 132.7174082860007, "count": 18202, "self": 132.7174082860007 } } }, "workers": { "total": 0.43962096499399195, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 622.6582273199894, "count": 18202, "is_parallel": true, "self": 290.9165285009926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00801333800006887, "count": 1, "is_parallel": true, "self": 0.004722160000142139, "children": { "_process_rank_one_or_two_observation": { "total": 0.003291177999926731, "count": 10, "is_parallel": true, "self": 0.003291177999926731 } } }, "UnityEnvironment.step": { "total": 0.08694252000009328, "count": 1, "is_parallel": true, "self": 0.0008685779999950682, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045996400001513393, "count": 1, "is_parallel": true, "self": 0.00045996400001513393 }, "communicator.exchange": { "total": 0.08344607100002577, "count": 1, "is_parallel": true, "self": 0.08344607100002577 }, "steps_from_proto": { "total": 0.002167907000057312, "count": 1, "is_parallel": true, "self": 0.00040152100007162517, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017663859999856868, "count": 10, "is_parallel": true, "self": 0.0017663859999856868 } } } } } } }, "UnityEnvironment.step": { "total": 331.7416988189967, "count": 18201, "is_parallel": true, "self": 15.22037656701059, "children": { "UnityEnvironment._generate_step_input": { "total": 8.033687076990418, "count": 18201, "is_parallel": true, "self": 8.033687076990418 }, "communicator.exchange": { "total": 262.1526269649962, "count": 18201, "is_parallel": true, "self": 262.1526269649962 }, "steps_from_proto": { "total": 46.3350082099995, "count": 18201, "is_parallel": true, "self": 9.276640202964813, "children": { "_process_rank_one_or_two_observation": { "total": 37.05836800703469, "count": 182010, "is_parallel": true, "self": 37.05836800703469 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0007718159999967611, "count": 1, "self": 0.0007718159999967611, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 614.1135922410357, "count": 640863, "is_parallel": true, "self": 15.329733126040423, "children": { "process_trajectory": { "total": 333.527762019996, "count": 640863, "is_parallel": true, "self": 332.9008631489959, "children": { "RLTrainer._checkpoint": { "total": 0.626898871000094, "count": 4, "is_parallel": true, "self": 0.626898871000094 } } }, "_update_policy": { "total": 265.2560970949993, "count": 90, "is_parallel": true, "self": 76.77446397900064, "children": { "TorchPPOOptimizer.update": { "total": 188.48163311599865, "count": 4587, "is_parallel": true, "self": 188.48163311599865 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09837784000001193, "count": 1, "self": 0.0012478609999106993, "children": { "RLTrainer._checkpoint": { "total": 0.09712997900010123, "count": 1, "self": 0.09712997900010123 } } } } } } }