{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7073879837989807, "min": 0.7073879837989807, "max": 2.85627818107605, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6754.140625, "min": 6754.140625, "max": 29251.14453125, "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": 12.954086303710938, "min": 0.333190381526947, "max": 12.954086303710938, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.046875, "min": 64.63893127441406, "max": 2598.26416015625, "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": 0.06822900095721707, "min": 0.06357364790621396, "max": 0.07617895118093264, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27291600382886827, "min": 0.25429459162485585, "max": 0.3734821413717702, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20661310376782044, "min": 0.12579575658652603, "max": 0.3049077070226856, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8264524150712818, "min": 0.5031830263461041, "max": 1.524538535113428, "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": 25.772727272727273, "min": 3.5681818181818183, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 157.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.5681818181818183, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 157.0, "max": 1393.0, "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": "1724330349", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724330922" }, "total": 572.564658283, "count": 1, "self": 0.4897001199999522, "children": { "run_training.setup": { "total": 0.06360568899998498, "count": 1, "self": 0.06360568899998498 }, "TrainerController.start_learning": { "total": 572.011352474, "count": 1, "self": 0.749136142998168, "children": { "TrainerController._reset_env": { "total": 3.4317776870000216, "count": 1, "self": 3.4317776870000216 }, "TrainerController.advance": { "total": 567.7266750900018, "count": 18200, "self": 0.3863128020018394, "children": { "env_step": { "total": 567.3403622879999, "count": 18200, "self": 373.24411448700954, "children": { "SubprocessEnvManager._take_step": { "total": 193.6860400180011, "count": 18200, "self": 2.0558677559877196, "children": { "TorchPolicy.evaluate": { "total": 191.6301722620134, "count": 18200, "self": 191.6301722620134 } } }, "workers": { "total": 0.41020778298928917, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 570.2694997429978, "count": 18200, "is_parallel": true, "self": 284.1719292749975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0062737789999687266, "count": 1, "is_parallel": true, "self": 0.004621710000037638, "children": { "_process_rank_one_or_two_observation": { "total": 0.001652068999931089, "count": 10, "is_parallel": true, "self": 0.001652068999931089 } } }, "UnityEnvironment.step": { "total": 0.09087277300000096, "count": 1, "is_parallel": true, "self": 0.0007132739999633486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046763000000282773, "count": 1, "is_parallel": true, "self": 0.00046763000000282773 }, "communicator.exchange": { "total": 0.08746658199999047, "count": 1, "is_parallel": true, "self": 0.08746658199999047 }, "steps_from_proto": { "total": 0.002225287000044318, "count": 1, "is_parallel": true, "self": 0.0004060620001951065, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018192249998492116, "count": 10, "is_parallel": true, "self": 0.0018192249998492116 } } } } } } }, "UnityEnvironment.step": { "total": 286.0975704680003, "count": 18199, "is_parallel": true, "self": 12.959504275993652, "children": { "UnityEnvironment._generate_step_input": { "total": 6.780539491003083, "count": 18199, "is_parallel": true, "self": 6.780539491003083 }, "communicator.exchange": { "total": 223.82659207000836, "count": 18199, "is_parallel": true, "self": 223.82659207000836 }, "steps_from_proto": { "total": 42.530934630995205, "count": 18199, "is_parallel": true, "self": 8.413134570997784, "children": { "_process_rank_one_or_two_observation": { "total": 34.11780005999742, "count": 181990, "is_parallel": true, "self": 34.11780005999742 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001905359999909706, "count": 1, "self": 0.0001905359999909706, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 560.324332587993, "count": 840906, "is_parallel": true, "self": 18.96768976894623, "children": { "process_trajectory": { "total": 312.29698030504704, "count": 840906, "is_parallel": true, "self": 311.57945667304693, "children": { "RLTrainer._checkpoint": { "total": 0.717523632000109, "count": 4, "is_parallel": true, "self": 0.717523632000109 } } }, "_update_policy": { "total": 229.0596625139998, "count": 90, "is_parallel": true, "self": 70.79513801199863, "children": { "TorchPPOOptimizer.update": { "total": 158.26452450200117, "count": 4587, "is_parallel": true, "self": 158.26452450200117 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10357301800002006, "count": 1, "self": 0.001086843000052795, "children": { "RLTrainer._checkpoint": { "total": 0.10248617499996726, "count": 1, "self": 0.10248617499996726 } } } } } } }