{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0281543731689453, "min": 1.0228270292282104, "max": 2.8651833534240723, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9839.4375, "min": 9839.4375, "max": 29373.859375, "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": 12.669914245605469, "min": 0.45945945382118225, "max": 12.669914245605469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2470.63330078125, "min": 89.1351318359375, "max": 2582.886962890625, "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": 0.06814597840277166, "min": 0.06430766494447074, "max": 0.07379015268639241, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27258391361108664, "min": 0.2635221391489419, "max": 0.3689507634319621, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20600613418455216, "min": 0.11048156735555761, "max": 0.27779950809245013, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8240245367382086, "min": 0.44192626942223046, "max": 1.3889975404622508, "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": 24.863636363636363, "min": 2.9318181818181817, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1094.0, "min": 129.0, "max": 1363.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.863636363636363, "min": 2.9318181818181817, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1094.0, "min": 129.0, "max": 1363.0, "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": "1687303442", "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": "1687303906" }, "total": 463.870854483, "count": 1, "self": 0.4335617969999248, "children": { "run_training.setup": { "total": 0.06889985899999829, "count": 1, "self": 0.06889985899999829 }, "TrainerController.start_learning": { "total": 463.3683928270001, "count": 1, "self": 0.5233187130072565, "children": { "TrainerController._reset_env": { "total": 4.3899469899999986, "count": 1, "self": 4.3899469899999986 }, "TrainerController.advance": { "total": 458.31617116299276, "count": 18204, "self": 0.24366390498551027, "children": { "env_step": { "total": 458.07250725800725, "count": 18204, "self": 334.54320777100145, "children": { "SubprocessEnvManager._take_step": { "total": 123.27686613599906, "count": 18204, "self": 1.7943114019897166, "children": { "TorchPolicy.evaluate": { "total": 121.48255473400934, "count": 18204, "self": 121.48255473400934 } } }, "workers": { "total": 0.2524333510067436, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 461.8245424860047, "count": 18204, "is_parallel": true, "self": 219.35534595300726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0066578329999629204, "count": 1, "is_parallel": true, "self": 0.004202797999823815, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024550350001391053, "count": 10, "is_parallel": true, "self": 0.0024550350001391053 } } }, "UnityEnvironment.step": { "total": 0.03532845699999143, "count": 1, "is_parallel": true, "self": 0.0006149089998643831, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034799500008375617, "count": 1, "is_parallel": true, "self": 0.00034799500008375617 }, "communicator.exchange": { "total": 0.03217408099999375, "count": 1, "is_parallel": true, "self": 0.03217408099999375 }, "steps_from_proto": { "total": 0.0021914720000495436, "count": 1, "is_parallel": true, "self": 0.00039870200032510184, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017927699997244417, "count": 10, "is_parallel": true, "self": 0.0017927699997244417 } } } } } } }, "UnityEnvironment.step": { "total": 242.46919653299744, "count": 18203, "is_parallel": true, "self": 10.4505702579944, "children": { "UnityEnvironment._generate_step_input": { "total": 5.223109731000591, "count": 18203, "is_parallel": true, "self": 5.223109731000591 }, "communicator.exchange": { "total": 192.40404747000184, "count": 18203, "is_parallel": true, "self": 192.40404747000184 }, "steps_from_proto": { "total": 34.39146907400061, "count": 18203, "is_parallel": true, "self": 6.219617513021717, "children": { "_process_rank_one_or_two_observation": { "total": 28.171851560978894, "count": 182030, "is_parallel": true, "self": 28.171851560978894 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011279000000286032, "count": 1, "self": 0.00011279000000286032, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.81836330298165, "count": 441708, "is_parallel": true, "self": 9.594221133935775, "children": { "process_trajectory": { "total": 245.72593900704624, "count": 441708, "is_parallel": true, "self": 244.41674080404619, "children": { "RLTrainer._checkpoint": { "total": 1.3091982030000509, "count": 4, "is_parallel": true, "self": 1.3091982030000509 } } }, "_update_policy": { "total": 199.49820316199964, "count": 90, "is_parallel": true, "self": 80.76087507399768, "children": { "TorchPPOOptimizer.update": { "total": 118.73732808800196, "count": 4584, "is_parallel": true, "self": 118.73732808800196 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13884317100007593, "count": 1, "self": 0.0008630909999283176, "children": { "RLTrainer._checkpoint": { "total": 0.1379800800001476, "count": 1, "self": 0.1379800800001476 } } } } } } }