{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0691092014312744, "min": 1.0691092014312744, "max": 1.5942479372024536, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10972.267578125, "min": 10888.201171875, "max": 16309.15625, "count": 10 }, "SnowballTarget.Step.mean": { "value": 299944.0, "min": 209936.0, "max": 299944.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 299944.0, "min": 209936.0, "max": 299944.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.593055725097656, "min": 10.063211441040039, "max": 12.593055725097656, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2568.9833984375, "min": 1932.1365966796875, "max": 2568.9833984375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.09090909090909, "min": 21.136363636363637, "max": 25.34090909090909, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1380.0, "min": 930.0, "max": 1393.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.09090909090909, "min": 21.136363636363637, "max": 25.34090909090909, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1380.0, "min": 930.0, "max": 1393.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06916270711671506, "min": 0.05830706287302104, "max": 0.07310536152149058, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.13832541423343012, "min": 0.11661412574604207, "max": 0.1972248834268505, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21709369035328135, "min": 0.20926002522601803, "max": 0.2832611144624929, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4341873807065627, "min": 0.4341873807065627, "max": 0.7940560870749109, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.376098207999998e-06, "min": 5.376098207999998e-06, "max": 9.337606887466668e-05, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0752196415999996e-05, "min": 1.0752196415999996e-05, "max": 0.00019432823522399996, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10179200000000001, "min": 0.10179200000000001, "max": 0.13112533333333337, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20358400000000001, "min": 0.20358400000000001, "max": 0.364776, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.942079999999998e-05, "min": 9.942079999999998e-05, "max": 0.0015631541333333333, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00019884159999999996, "min": 0.00019884159999999996, "max": 0.003262322400000001, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702854464", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702854685" }, "total": 220.82709319900005, "count": 1, "self": 0.6029564710001978, "children": { "run_training.setup": { "total": 0.056017914999983986, "count": 1, "self": 0.056017914999983986 }, "TrainerController.start_learning": { "total": 220.16811881299986, "count": 1, "self": 0.33025679398633656, "children": { "TrainerController._reset_env": { "total": 2.0461344620000546, "count": 1, "self": 2.0461344620000546 }, "TrainerController.advance": { "total": 217.58931440201354, "count": 9132, "self": 0.13580619401659533, "children": { "env_step": { "total": 217.45350820799695, "count": 9132, "self": 148.38303226201378, "children": { "SubprocessEnvManager._take_step": { "total": 68.92934167998396, "count": 9132, "self": 0.7219665359930332, "children": { "TorchPolicy.evaluate": { "total": 68.20737514399093, "count": 9132, "self": 68.20737514399093 } } }, "workers": { "total": 0.14113426599919876, "count": 9132, "self": 0.0, "children": { "worker_root": { "total": 219.39355299799695, "count": 9132, "is_parallel": true, "self": 107.01856439499534, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016263719999187742, "count": 1, "is_parallel": true, "self": 0.00047473800032094005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011516339995978342, "count": 10, "is_parallel": true, "self": 0.0011516339995978342 } } }, "UnityEnvironment.step": { "total": 0.03596235300005901, "count": 1, "is_parallel": true, "self": 0.0006419720002668328, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004035790000216366, "count": 1, "is_parallel": true, "self": 0.0004035790000216366 }, "communicator.exchange": { "total": 0.03301259499994558, "count": 1, "is_parallel": true, "self": 0.03301259499994558 }, "steps_from_proto": { "total": 0.0019042069998249644, "count": 1, "is_parallel": true, "self": 0.00038447399970209517, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015197330001228693, "count": 10, "is_parallel": true, "self": 0.0015197330001228693 } } } } } } }, "UnityEnvironment.step": { "total": 112.37498860300161, "count": 9131, "is_parallel": true, "self": 5.284206426007586, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6740532879891816, "count": 9131, "is_parallel": true, "self": 2.6740532879891816 }, "communicator.exchange": { "total": 87.90271529498432, "count": 9131, "is_parallel": true, "self": 87.90271529498432 }, "steps_from_proto": { "total": 16.514013594020525, "count": 9131, "is_parallel": true, "self": 3.078017339043754, "children": { "_process_rank_one_or_two_observation": { "total": 13.435996254976772, "count": 91310, "is_parallel": true, "self": 13.435996254976772 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004031409998788149, "count": 1, "self": 0.0004031409998788149, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 213.92445111497977, "count": 444850, "is_parallel": true, "self": 9.002163526009326, "children": { "process_trajectory": { "total": 150.38162959797, "count": 444850, "is_parallel": true, "self": 149.88418699196995, "children": { "RLTrainer._checkpoint": { "total": 0.49744260600004964, "count": 2, "is_parallel": true, "self": 0.49744260600004964 } } }, "_update_policy": { "total": 54.540657991000444, "count": 22, "is_parallel": true, "self": 17.89772584499974, "children": { "TorchPPOOptimizer.update": { "total": 36.6429321460007, "count": 1494, "is_parallel": true, "self": 36.6429321460007 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20201001400005225, "count": 1, "self": 0.004421799000056126, "children": { "RLTrainer._checkpoint": { "total": 0.19758821499999613, "count": 1, "self": 0.19758821499999613 } } } } } } }