{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9516487717628479, "min": 0.9516487717628479, "max": 2.8539583683013916, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9096.810546875, "min": 9096.810546875, "max": 29258.78125, "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": 13.193964958190918, "min": 0.3793833255767822, "max": 13.193964958190918, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2572.8232421875, "min": 73.6003646850586, "max": 2661.947998046875, "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": 0.0711851676190717, "min": 0.06120544754644382, "max": 0.07563325980513849, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2847406704762868, "min": 0.24482179018577527, "max": 0.37816629902569243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18710351487000784, "min": 0.10398653764551616, "max": 0.27143652322245576, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7484140594800314, "min": 0.41594615058206463, "max": 1.3571826161122789, "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": 26.477272727272727, "min": 2.8863636363636362, "max": 26.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1165.0, "min": 127.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.477272727272727, "min": 2.8863636363636362, "max": 26.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1165.0, "min": 127.0, "max": 1400.0, "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": "1681292328", "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 ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681292776" }, "total": 448.6115815999999, "count": 1, "self": 0.37929366200000914, "children": { "run_training.setup": { "total": 0.10443965800004662, "count": 1, "self": 0.10443965800004662 }, "TrainerController.start_learning": { "total": 448.12784827999985, "count": 1, "self": 0.531488217968672, "children": { "TrainerController._reset_env": { "total": 4.007220469999993, "count": 1, "self": 4.007220469999993 }, "TrainerController.advance": { "total": 443.45151271503073, "count": 18203, "self": 0.26565998104683786, "children": { "env_step": { "total": 443.1858527339839, "count": 18203, "self": 328.5417133609817, "children": { "SubprocessEnvManager._take_step": { "total": 114.38048088798928, "count": 18203, "self": 1.7173421879972466, "children": { "TorchPolicy.evaluate": { "total": 112.66313869999203, "count": 18203, "self": 112.66313869999203 } } }, "workers": { "total": 0.2636584850129111, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 446.7343343270254, "count": 18203, "is_parallel": true, "self": 206.38177627201935, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018779340000492084, "count": 1, "is_parallel": true, "self": 0.0005310360002113157, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013468979998378927, "count": 10, "is_parallel": true, "self": 0.0013468979998378927 } } }, "UnityEnvironment.step": { "total": 0.08789647599996897, "count": 1, "is_parallel": true, "self": 0.0005885399998533103, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003675560001283884, "count": 1, "is_parallel": true, "self": 0.0003675560001283884 }, "communicator.exchange": { "total": 0.08509902199989483, "count": 1, "is_parallel": true, "self": 0.08509902199989483 }, "steps_from_proto": { "total": 0.0018413580000924412, "count": 1, "is_parallel": true, "self": 0.0004093610002655623, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014319969998268789, "count": 10, "is_parallel": true, "self": 0.0014319969998268789 } } } } } } }, "UnityEnvironment.step": { "total": 240.35255805500606, "count": 18202, "is_parallel": true, "self": 9.558775452016562, "children": { "UnityEnvironment._generate_step_input": { "total": 5.152822202001971, "count": 18202, "is_parallel": true, "self": 5.152822202001971 }, "communicator.exchange": { "total": 195.19558472799827, "count": 18202, "is_parallel": true, "self": 195.19558472799827 }, "steps_from_proto": { "total": 30.445375672989258, "count": 18202, "is_parallel": true, "self": 5.958778968024035, "children": { "_process_rank_one_or_two_observation": { "total": 24.486596704965223, "count": 182020, "is_parallel": true, "self": 24.486596704965223 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014235500020731706, "count": 1, "self": 0.00014235500020731706, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 440.2278282888151, "count": 392686, "is_parallel": true, "self": 9.38862173474945, "children": { "process_trajectory": { "total": 241.661898202065, "count": 392686, "is_parallel": true, "self": 240.5777575160655, "children": { "RLTrainer._checkpoint": { "total": 1.0841406859995004, "count": 4, "is_parallel": true, "self": 1.0841406859995004 } } }, "_update_policy": { "total": 189.17730835200064, "count": 90, "is_parallel": true, "self": 73.69973795200167, "children": { "TorchPPOOptimizer.update": { "total": 115.47757039999897, "count": 4587, "is_parallel": true, "self": 115.47757039999897 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13748452200024985, "count": 1, "self": 0.0008958170001278631, "children": { "RLTrainer._checkpoint": { "total": 0.136588705000122, "count": 1, "self": 0.136588705000122 } } } } } } }