{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0338046550750732, "min": 1.0338046550750732, "max": 2.8685336112976074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9904.8818359375, "min": 9904.8818359375, "max": 29408.20703125, "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": 12.918645858764648, "min": 0.3445725440979004, "max": 12.918645858764648, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.135986328125, "min": 66.84707641601562, "max": 2611.3583984375, "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": 0.0698584218700097, "min": 0.061859704459350844, "max": 0.07402423659029106, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2794336874800388, "min": 0.24743881783740337, "max": 0.3701211829514553, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18587966274250955, "min": 0.11828432025732565, "max": 0.2887558902595558, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7435186509700382, "min": 0.4731372810293026, "max": 1.4437794512977788, "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": 25.34090909090909, "min": 3.522727272727273, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 155.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 3.522727272727273, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 155.0, "max": 1378.0, "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": "1682499497", "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": "1682499956" }, "total": 458.65997608099997, "count": 1, "self": 0.7535235249999914, "children": { "run_training.setup": { "total": 0.12595672199995533, "count": 1, "self": 0.12595672199995533 }, "TrainerController.start_learning": { "total": 457.780495834, "count": 1, "self": 0.5237704450139518, "children": { "TrainerController._reset_env": { "total": 3.981484179000063, "count": 1, "self": 3.981484179000063 }, "TrainerController.advance": { "total": 453.06543966798586, "count": 18217, "self": 0.26191018499594065, "children": { "env_step": { "total": 452.8035294829899, "count": 18217, "self": 330.2522687259932, "children": { "SubprocessEnvManager._take_step": { "total": 122.28570108799522, "count": 18217, "self": 1.6340852540124615, "children": { "TorchPolicy.evaluate": { "total": 120.65161583398276, "count": 18217, "self": 120.65161583398276 } } }, "workers": { "total": 0.2655596690015045, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 456.1262519299703, "count": 18217, "is_parallel": true, "self": 213.05910300196638, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005441735999966113, "count": 1, "is_parallel": true, "self": 0.0040796089997456875, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013621270002204255, "count": 10, "is_parallel": true, "self": 0.0013621270002204255 } } }, "UnityEnvironment.step": { "total": 0.03483044099994004, "count": 1, "is_parallel": true, "self": 0.0005635940001411655, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003184469999268913, "count": 1, "is_parallel": true, "self": 0.0003184469999268913 }, "communicator.exchange": { "total": 0.03201261799995336, "count": 1, "is_parallel": true, "self": 0.03201261799995336 }, "steps_from_proto": { "total": 0.0019357819999186177, "count": 1, "is_parallel": true, "self": 0.00040359400031775294, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015321879996008647, "count": 10, "is_parallel": true, "self": 0.0015321879996008647 } } } } } } }, "UnityEnvironment.step": { "total": 243.06714892800392, "count": 18216, "is_parallel": true, "self": 9.812663722001616, "children": { "UnityEnvironment._generate_step_input": { "total": 5.413491566019047, "count": 18216, "is_parallel": true, "self": 5.413491566019047 }, "communicator.exchange": { "total": 196.07956713100384, "count": 18216, "is_parallel": true, "self": 196.07956713100384 }, "steps_from_proto": { "total": 31.76142650897941, "count": 18216, "is_parallel": true, "self": 6.2441115739832185, "children": { "_process_rank_one_or_two_observation": { "total": 25.517314934996193, "count": 182160, "is_parallel": true, "self": 25.517314934996193 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.7622000137344e-05, "count": 1, "self": 8.7622000137344e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 449.4186360259964, "count": 412890, "is_parallel": true, "self": 10.26880700701281, "children": { "process_trajectory": { "total": 248.01273882498185, "count": 412890, "is_parallel": true, "self": 246.37549554498173, "children": { "RLTrainer._checkpoint": { "total": 1.6372432800001206, "count": 4, "is_parallel": true, "self": 1.6372432800001206 } } }, "_update_policy": { "total": 191.13709019400176, "count": 90, "is_parallel": true, "self": 71.41216488200325, "children": { "TorchPPOOptimizer.update": { "total": 119.7249253119985, "count": 4584, "is_parallel": true, "self": 119.7249253119985 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20971392000001288, "count": 1, "self": 0.0011501230001158547, "children": { "RLTrainer._checkpoint": { "total": 0.20856379699989702, "count": 1, "self": 0.20856379699989702 } } } } } } }