{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.961064338684082, "min": 0.961064338684082, "max": 2.8516974449157715, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9218.529296875, "min": 9218.529296875, "max": 29266.970703125, "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": 12.596700668334961, "min": 0.22807639837265015, "max": 12.596700668334961, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2456.356689453125, "min": 44.246822357177734, "max": 2543.736328125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0637166382731783, "min": 0.06143302182494618, "max": 0.07541322153867405, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2548665530927132, "min": 0.2488086171899483, "max": 0.37706610769337023, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22664793945995032, "min": 0.11199139757081866, "max": 0.2807696834498761, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9065917578398013, "min": 0.44796559028327465, "max": 1.4038484172493804, "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": 24.704545454545453, "min": 3.1363636363636362, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1087.0, "min": 138.0, "max": 1361.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.704545454545453, "min": 3.1363636363636362, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1087.0, "min": 138.0, "max": 1361.0, "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": "1705308092", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/mnt/wsl/PHYSICALDRIVE0p1/akira/Works/src/github.com/Unity-Technologies/ml-agents/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1", "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": "1705308610" }, "total": 517.6926009320014, "count": 1, "self": 0.32058491900534136, "children": { "run_training.setup": { "total": 0.02123655399918789, "count": 1, "self": 0.02123655399918789 }, "TrainerController.start_learning": { "total": 517.3507794589968, "count": 1, "self": 0.4891007944752346, "children": { "TrainerController._reset_env": { "total": 5.305420818003768, "count": 1, "self": 5.305420818003768 }, "TrainerController.advance": { "total": 511.483563208516, "count": 18203, "self": 0.24071318141795928, "children": { "env_step": { "total": 511.24285002709803, "count": 18203, "self": 306.1718886025337, "children": { "SubprocessEnvManager._take_step": { "total": 204.82909008219576, "count": 18203, "self": 1.3016690048389137, "children": { "TorchPolicy.evaluate": { "total": 203.52742107735685, "count": 18203, "self": 203.52742107735685 } } }, "workers": { "total": 0.24187134236854035, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 516.4308452459663, "count": 18203, "is_parallel": true, "self": 292.05595707489556, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003437626000959426, "count": 1, "is_parallel": true, "self": 0.0011196710183867253, "children": { "_process_rank_one_or_two_observation": { "total": 0.002317954982572701, "count": 10, "is_parallel": true, "self": 0.002317954982572701 } } }, "UnityEnvironment.step": { "total": 0.027147358996444382, "count": 1, "is_parallel": true, "self": 0.0002403370017418638, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002150329964933917, "count": 1, "is_parallel": true, "self": 0.0002150329964933917 }, "communicator.exchange": { "total": 0.02579365199926542, "count": 1, "is_parallel": true, "self": 0.02579365199926542 }, "steps_from_proto": { "total": 0.0008983369989437051, "count": 1, "is_parallel": true, "self": 0.00024643900542287156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006518979935208336, "count": 10, "is_parallel": true, "self": 0.0006518979935208336 } } } } } } }, "UnityEnvironment.step": { "total": 224.37488817107078, "count": 18202, "is_parallel": true, "self": 4.787767729903862, "children": { "UnityEnvironment._generate_step_input": { "total": 3.1225529659859603, "count": 18202, "is_parallel": true, "self": 3.1225529659859603 }, "communicator.exchange": { "total": 200.63608249132085, "count": 18202, "is_parallel": true, "self": 200.63608249132085 }, "steps_from_proto": { "total": 15.828484983860108, "count": 18202, "is_parallel": true, "self": 4.067843757024093, "children": { "_process_rank_one_or_two_observation": { "total": 11.760641226836015, "count": 182020, "is_parallel": true, "self": 11.760641226836015 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.111400140682235e-05, "count": 1, "self": 9.111400140682235e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 509.6809919526713, "count": 331969, "is_parallel": true, "self": 5.2720681143473485, "children": { "process_trajectory": { "total": 285.8810730863188, "count": 331969, "is_parallel": true, "self": 285.3537578923133, "children": { "RLTrainer._checkpoint": { "total": 0.5273151940054959, "count": 4, "is_parallel": true, "self": 0.5273151940054959 } } }, "_update_policy": { "total": 218.52785075200518, "count": 90, "is_parallel": true, "self": 33.037342100637034, "children": { "TorchPPOOptimizer.update": { "total": 185.49050865136815, "count": 4587, "is_parallel": true, "self": 185.49050865136815 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07260352400044212, "count": 1, "self": 0.0005582859957939945, "children": { "RLTrainer._checkpoint": { "total": 0.07204523800464813, "count": 1, "self": 0.07204523800464813 } } } } } } }