{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3009757995605469, "min": 1.3009757995605469, "max": 2.8832619190216064, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12450.3388671875, "min": 12450.3388671875, "max": 29590.916015625, "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": 10.78321361541748, "min": 0.1922581046819687, "max": 10.78321361541748, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2102.7265625, "min": 37.298072814941406, "max": 2138.6083984375, "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.Environment.CumulativeReward.mean": { "value": 23.272727272727273, "min": 3.0, "max": 23.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1024.0, "min": 132.0, "max": 1219.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.272727272727273, "min": 3.0, "max": 23.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1024.0, "min": 132.0, "max": 1219.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04854722280173983, "min": 0.040722295108614213, "max": 0.054452556641479445, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.09709444560347966, "min": 0.08144459021722843, "max": 0.16335766992443834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2527855062017254, "min": 0.10304775325508386, "max": 0.3152477364329731, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5055710124034508, "min": 0.20609550651016773, "max": 0.8257487837006063, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.432097856000005e-06, "min": 6.432097856000005e-06, "max": 0.00029023200325600004, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.286419571200001e-05, "min": 1.286419571200001e-05, "max": 0.0007422840525719999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102144, "min": 0.102144, "max": 0.196744, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.204288, "min": 0.204288, "max": 0.5474280000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011698560000000007, "min": 0.00011698560000000007, "max": 0.0048375256, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023397120000000015, "min": 0.00023397120000000015, "max": 0.012376657199999998, "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": "1699625658", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699626121" }, "total": 462.94353993100003, "count": 1, "self": 0.6918987740000375, "children": { "run_training.setup": { "total": 0.07031105900000512, "count": 1, "self": 0.07031105900000512 }, "TrainerController.start_learning": { "total": 462.181330098, "count": 1, "self": 0.5387673159966653, "children": { "TrainerController._reset_env": { "total": 11.40669449500001, "count": 1, "self": 11.40669449500001 }, "TrainerController.advance": { "total": 450.0789563270032, "count": 18203, "self": 0.247867750975729, "children": { "env_step": { "total": 449.83108857602747, "count": 18203, "self": 309.5904530520179, "children": { "SubprocessEnvManager._take_step": { "total": 139.97096221898823, "count": 18203, "self": 1.4068417709968344, "children": { "TorchPolicy.evaluate": { "total": 138.5641204479914, "count": 18203, "self": 138.5641204479914 } } }, "workers": { "total": 0.26967330502134246, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 461.0132925789869, "count": 18203, "is_parallel": true, "self": 223.4307308279865, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007152268000027107, "count": 1, "is_parallel": true, "self": 0.004202289999966524, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029499780000605824, "count": 10, "is_parallel": true, "self": 0.0029499780000605824 } } }, "UnityEnvironment.step": { "total": 0.06792309699994803, "count": 1, "is_parallel": true, "self": 0.0006344939999962662, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004126659998746618, "count": 1, "is_parallel": true, "self": 0.0004126659998746618 }, "communicator.exchange": { "total": 0.0650125909999133, "count": 1, "is_parallel": true, "self": 0.0650125909999133 }, "steps_from_proto": { "total": 0.0018633460001638014, "count": 1, "is_parallel": true, "self": 0.0003962299999784591, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014671160001853423, "count": 10, "is_parallel": true, "self": 0.0014671160001853423 } } } } } } }, "UnityEnvironment.step": { "total": 237.5825617510004, "count": 18202, "is_parallel": true, "self": 10.608044900001005, "children": { "UnityEnvironment._generate_step_input": { "total": 5.377869183996154, "count": 18202, "is_parallel": true, "self": 5.377869183996154 }, "communicator.exchange": { "total": 187.66467389399918, "count": 18202, "is_parallel": true, "self": 187.66467389399918 }, "steps_from_proto": { "total": 33.931973773004074, "count": 18202, "is_parallel": true, "self": 6.300384587997996, "children": { "_process_rank_one_or_two_observation": { "total": 27.631589185006078, "count": 182020, "is_parallel": true, "self": 27.631589185006078 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014500400016004278, "count": 1, "self": 0.00014500400016004278, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.0605960031178, "count": 590460, "is_parallel": true, "self": 12.854787390098636, "children": { "process_trajectory": { "total": 313.0158412390192, "count": 590460, "is_parallel": true, "self": 311.9401254470192, "children": { "RLTrainer._checkpoint": { "total": 1.0757157919999827, "count": 4, "is_parallel": true, "self": 1.0757157919999827 } } }, "_update_policy": { "total": 119.18996737399993, "count": 45, "is_parallel": true, "self": 52.40173951000088, "children": { "TorchPPOOptimizer.update": { "total": 66.78822786399905, "count": 2289, "is_parallel": true, "self": 66.78822786399905 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15676695599995583, "count": 1, "self": 0.0014289650000591791, "children": { "RLTrainer._checkpoint": { "total": 0.15533799099989665, "count": 1, "self": 0.15533799099989665 } } } } } } }