{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.116557240486145, "min": 1.116557240486145, "max": 2.8617780208587646, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10660.888671875, "min": 10660.888671875, "max": 29307.46875, "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": 11.878549575805664, "min": 0.3352653980255127, "max": 11.878549575805664, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2316.317138671875, "min": 65.04148864746094, "max": 2375.4853515625, "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": 0.07585151151978803, "min": 0.06420048370871205, "max": 0.08350901610866261, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3034060460791521, "min": 0.264623391533307, "max": 0.4175450805433131, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20630103787955117, "min": 0.1189633379941441, "max": 0.27108834917638813, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8252041515182047, "min": 0.4758533519765764, "max": 1.3554417458819408, "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": 23.931818181818183, "min": 3.522727272727273, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1053.0, "min": 155.0, "max": 1300.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.931818181818183, "min": 3.522727272727273, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1053.0, "min": 155.0, "max": 1300.0, "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": "1682006799", "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": "1682007276" }, "total": 476.43773064999993, "count": 1, "self": 0.43029804399998284, "children": { "run_training.setup": { "total": 0.11764611199998853, "count": 1, "self": 0.11764611199998853 }, "TrainerController.start_learning": { "total": 475.88978649399996, "count": 1, "self": 0.57133437800303, "children": { "TrainerController._reset_env": { "total": 4.0506469519999655, "count": 1, "self": 4.0506469519999655 }, "TrainerController.advance": { "total": 471.14207242699706, "count": 18201, "self": 0.30526691599277456, "children": { "env_step": { "total": 470.8368055110043, "count": 18201, "self": 342.49388632598993, "children": { "SubprocessEnvManager._take_step": { "total": 128.04623856300896, "count": 18201, "self": 2.00006774701842, "children": { "TorchPolicy.evaluate": { "total": 126.04617081599054, "count": 18201, "self": 126.04617081599054 } } }, "workers": { "total": 0.2966806220053968, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 474.2655957109855, "count": 18201, "is_parallel": true, "self": 218.45706612098297, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00507756700005757, "count": 1, "is_parallel": true, "self": 0.0034716530000196144, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016059140000379557, "count": 10, "is_parallel": true, "self": 0.0016059140000379557 } } }, "UnityEnvironment.step": { "total": 0.038616725999986556, "count": 1, "is_parallel": true, "self": 0.0005903110001099776, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003851449999956458, "count": 1, "is_parallel": true, "self": 0.0003851449999956458 }, "communicator.exchange": { "total": 0.035452087999942705, "count": 1, "is_parallel": true, "self": 0.035452087999942705 }, "steps_from_proto": { "total": 0.002189181999938228, "count": 1, "is_parallel": true, "self": 0.00042055000028540235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017686319996528255, "count": 10, "is_parallel": true, "self": 0.0017686319996528255 } } } } } } }, "UnityEnvironment.step": { "total": 255.80852959000254, "count": 18200, "is_parallel": true, "self": 10.234083643024064, "children": { "UnityEnvironment._generate_step_input": { "total": 5.798266176987681, "count": 18200, "is_parallel": true, "self": 5.798266176987681 }, "communicator.exchange": { "total": 205.50398474599467, "count": 18200, "is_parallel": true, "self": 205.50398474599467 }, "steps_from_proto": { "total": 34.27219502399612, "count": 18200, "is_parallel": true, "self": 6.866667731978055, "children": { "_process_rank_one_or_two_observation": { "total": 27.405527292018064, "count": 182000, "is_parallel": true, "self": 27.405527292018064 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011826599984487984, "count": 1, "self": 0.00011826599984487984, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 467.4544792029359, "count": 440659, "is_parallel": true, "self": 11.024355653901011, "children": { "process_trajectory": { "total": 260.6176533750339, "count": 440659, "is_parallel": true, "self": 259.8730621600338, "children": { "RLTrainer._checkpoint": { "total": 0.7445912150001277, "count": 4, "is_parallel": true, "self": 0.7445912150001277 } } }, "_update_policy": { "total": 195.81247017400096, "count": 90, "is_parallel": true, "self": 71.49371292399996, "children": { "TorchPPOOptimizer.update": { "total": 124.318757250001, "count": 4587, "is_parallel": true, "self": 124.318757250001 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12561447100006262, "count": 1, "self": 0.0009093869998650916, "children": { "RLTrainer._checkpoint": { "total": 0.12470508400019753, "count": 1, "self": 0.12470508400019753 } } } } } } }