{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0846397876739502, "min": 1.0846397876739502, "max": 2.8685317039489746, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10368.072265625, "min": 10368.072265625, "max": 29376.6328125, "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": 12.184429168701172, "min": 0.37016937136650085, "max": 12.184429168701172, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2375.963623046875, "min": 71.81285858154297, "max": 2455.0126953125, "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": 0.06740611942494106, "min": 0.061216191117030874, "max": 0.07695894195999513, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2696244776997642, "min": 0.2696244776997642, "max": 0.35199895402297887, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1972603094124911, "min": 0.12603665724072569, "max": 0.2826918191185185, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7890412376499644, "min": 0.5041466289629027, "max": 1.4134590955925923, "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": 23.84090909090909, "min": 3.159090909090909, "max": 24.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1049.0, "min": 139.0, "max": 1314.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.84090909090909, "min": 3.159090909090909, "max": 24.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1049.0, "min": 139.0, "max": 1314.0, "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": "1697548133", "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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697548626" }, "total": 493.60815260999993, "count": 1, "self": 0.7921343739999429, "children": { "run_training.setup": { "total": 0.05134665200000654, "count": 1, "self": 0.05134665200000654 }, "TrainerController.start_learning": { "total": 492.764671584, "count": 1, "self": 0.5534288519956476, "children": { "TrainerController._reset_env": { "total": 7.620875312999999, "count": 1, "self": 7.620875312999999 }, "TrainerController.advance": { "total": 484.48775717700437, "count": 18200, "self": 0.2762366820103921, "children": { "env_step": { "total": 484.211520494994, "count": 18200, "self": 331.1946393399922, "children": { "SubprocessEnvManager._take_step": { "total": 152.7351899290042, "count": 18200, "self": 1.503924248996043, "children": { "TorchPolicy.evaluate": { "total": 151.23126568000816, "count": 18200, "self": 151.23126568000816 } } }, "workers": { "total": 0.28169122599757657, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 491.5663572709978, "count": 18200, "is_parallel": true, "self": 238.16820384899978, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005738527000005433, "count": 1, "is_parallel": true, "self": 0.0042251389999137245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015133880000917088, "count": 10, "is_parallel": true, "self": 0.0015133880000917088 } } }, "UnityEnvironment.step": { "total": 0.07313139500001853, "count": 1, "is_parallel": true, "self": 0.0007060400000113987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000469984000005752, "count": 1, "is_parallel": true, "self": 0.000469984000005752 }, "communicator.exchange": { "total": 0.07009639599999673, "count": 1, "is_parallel": true, "self": 0.07009639599999673 }, "steps_from_proto": { "total": 0.0018589750000046479, "count": 1, "is_parallel": true, "self": 0.00035329800005001744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015056769999546304, "count": 10, "is_parallel": true, "self": 0.0015056769999546304 } } } } } } }, "UnityEnvironment.step": { "total": 253.39815342199802, "count": 18199, "is_parallel": true, "self": 11.415809037995018, "children": { "UnityEnvironment._generate_step_input": { "total": 5.841074232011579, "count": 18199, "is_parallel": true, "self": 5.841074232011579 }, "communicator.exchange": { "total": 200.02755851199038, "count": 18199, "is_parallel": true, "self": 200.02755851199038 }, "steps_from_proto": { "total": 36.11371164000104, "count": 18199, "is_parallel": true, "self": 6.791787885984547, "children": { "_process_rank_one_or_two_observation": { "total": 29.321923754016495, "count": 181990, "is_parallel": true, "self": 29.321923754016495 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001379259999794158, "count": 1, "self": 0.0001379259999794158, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 480.3230959480461, "count": 497593, "is_parallel": true, "self": 11.027840453030592, "children": { "process_trajectory": { "total": 270.8551540570155, "count": 497593, "is_parallel": true, "self": 269.93054430401554, "children": { "RLTrainer._checkpoint": { "total": 0.9246097529999702, "count": 4, "is_parallel": true, "self": 0.9246097529999702 } } }, "_update_policy": { "total": 198.440101438, "count": 90, "is_parallel": true, "self": 62.352226613999676, "children": { "TorchPPOOptimizer.update": { "total": 136.08787482400032, "count": 4587, "is_parallel": true, "self": 136.08787482400032 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1024723159999894, "count": 1, "self": 0.0013679779999620223, "children": { "RLTrainer._checkpoint": { "total": 0.10110433800002738, "count": 1, "self": 0.10110433800002738 } } } } } } }