{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9208049774169922, "min": 0.9208049774169922, "max": 2.867793321609497, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8801.974609375, "min": 8801.974609375, "max": 29369.0703125, "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": 12.798652648925781, "min": 0.41426512598991394, "max": 12.798652648925781, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.7373046875, "min": 80.367431640625, "max": 2593.8740234375, "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": 0.06849672533123749, "min": 0.06212536432726398, "max": 0.0746873482071975, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27398690132494996, "min": 0.24850145730905593, "max": 0.36275760343432567, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18312071537708535, "min": 0.11268239729357518, "max": 0.2829885007996185, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7324828615083414, "min": 0.4507295891743007, "max": 1.3897062160220799, "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": 25.454545454545453, "min": 3.3181818181818183, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 146.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.3181818181818183, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 146.0, "max": 1386.0, "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": "1686935895", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686936375" }, "total": 479.79437718099985, "count": 1, "self": 0.4341349099997842, "children": { "run_training.setup": { "total": 0.04541929300012271, "count": 1, "self": 0.04541929300012271 }, "TrainerController.start_learning": { "total": 479.31482297799994, "count": 1, "self": 0.5799223450146656, "children": { "TrainerController._reset_env": { "total": 4.396687567000072, "count": 1, "self": 4.396687567000072 }, "TrainerController.advance": { "total": 474.1919904769852, "count": 18202, "self": 0.27297571198505466, "children": { "env_step": { "total": 473.91901476500016, "count": 18202, "self": 344.2233115669849, "children": { "SubprocessEnvManager._take_step": { "total": 129.42180788900396, "count": 18202, "self": 1.724410346025934, "children": { "TorchPolicy.evaluate": { "total": 127.69739754297802, "count": 18202, "self": 127.69739754297802 } } }, "workers": { "total": 0.27389530901132275, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 477.7663424699879, "count": 18202, "is_parallel": true, "self": 222.5283905899962, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005513346000043384, "count": 1, "is_parallel": true, "self": 0.0038519690003795404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016613769996638439, "count": 10, "is_parallel": true, "self": 0.0016613769996638439 } } }, "UnityEnvironment.step": { "total": 0.03615994699998737, "count": 1, "is_parallel": true, "self": 0.0006006800001614465, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033699300001899246, "count": 1, "is_parallel": true, "self": 0.00033699300001899246 }, "communicator.exchange": { "total": 0.03316029999996317, "count": 1, "is_parallel": true, "self": 0.03316029999996317 }, "steps_from_proto": { "total": 0.002061973999843758, "count": 1, "is_parallel": true, "self": 0.00036088899923925055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017010850006045075, "count": 10, "is_parallel": true, "self": 0.0017010850006045075 } } } } } } }, "UnityEnvironment.step": { "total": 255.23795187999167, "count": 18201, "is_parallel": true, "self": 10.633408257003339, "children": { "UnityEnvironment._generate_step_input": { "total": 5.378351438997015, "count": 18201, "is_parallel": true, "self": 5.378351438997015 }, "communicator.exchange": { "total": 203.5035084729891, "count": 18201, "is_parallel": true, "self": 203.5035084729891 }, "steps_from_proto": { "total": 35.72268371100222, "count": 18201, "is_parallel": true, "self": 6.4833577080405576, "children": { "_process_rank_one_or_two_observation": { "total": 29.23932600296166, "count": 182010, "is_parallel": true, "self": 29.23932600296166 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012058699985573185, "count": 1, "self": 0.00012058699985573185, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.508980250994, "count": 460479, "is_parallel": true, "self": 10.00454692903213, "children": { "process_trajectory": { "total": 258.85124084096174, "count": 460479, "is_parallel": true, "self": 258.06306701696167, "children": { "RLTrainer._checkpoint": { "total": 0.7881738240000686, "count": 4, "is_parallel": true, "self": 0.7881738240000686 } } }, "_update_policy": { "total": 201.65319248100013, "count": 90, "is_parallel": true, "self": 74.24901526300141, "children": { "TorchPPOOptimizer.update": { "total": 127.40417721799872, "count": 4587, "is_parallel": true, "self": 127.40417721799872 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14610200200013423, "count": 1, "self": 0.0008858510002482944, "children": { "RLTrainer._checkpoint": { "total": 0.14521615099988594, "count": 1, "self": 0.14521615099988594 } } } } } } }