{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1061533689498901, "min": 1.1061533689498901, "max": 2.8807127475738525, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10610.2236328125, "min": 10597.0703125, "max": 29406.31640625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 27.15814208984375, "min": 0.14902353286743164, "max": 27.15814208984375, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 5567.4189453125, "min": 28.910564422607422, "max": 5567.4189453125, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.072727272727274, "min": 2.659090909090909, "max": 27.472727272727273, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1489.0, "min": 117.0, "max": 1511.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.072727272727274, "min": 2.659090909090909, "max": 27.472727272727273, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1489.0, "min": 117.0, "max": 1511.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04618689578038517, "min": 0.03853284670856952, "max": 0.05633516705112176, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.09237379156077034, "min": 0.07706569341713904, "max": 0.15253684486122115, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1920968969078625, "min": 0.11202401665436543, "max": 0.33624354552696734, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.384193793815725, "min": 0.22404803330873085, "max": 0.9512951913125375, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000066e-06, "min": 3.0528989824000066e-06, "max": 0.00029609280130239995, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.105797964800013e-06, "min": 6.105797964800013e-06, "max": 0.0008367984210671999, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10050879999999998, "min": 0.10050879999999998, "max": 0.14934879999999995, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20101759999999996, "min": 0.20101759999999996, "max": 0.43946640000000003, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001116582400000002, "min": 0.0001116582400000002, "max": 0.009869890240000002, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002233164800000004, "min": 0.0002233164800000004, "max": 0.02789538672, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736359575", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736360751" }, "total": 1176.127138062, "count": 1, "self": 0.4755067799999324, "children": { "run_training.setup": { "total": 0.06490787000007003, "count": 1, "self": 0.06490787000007003 }, "TrainerController.start_learning": { "total": 1175.586723412, "count": 1, "self": 0.9535556829864618, "children": { "TrainerController._reset_env": { "total": 6.780620624999983, "count": 1, "self": 6.780620624999983 }, "TrainerController.advance": { "total": 1167.744188133014, "count": 45464, "self": 1.0275872040285776, "children": { "env_step": { "total": 817.1551970450143, "count": 45464, "self": 621.4129901820344, "children": { "SubprocessEnvManager._take_step": { "total": 195.16706459999148, "count": 45464, "self": 3.3594348019623794, "children": { "TorchPolicy.evaluate": { "total": 191.8076297980291, "count": 45464, "self": 191.8076297980291 } } }, "workers": { "total": 0.5751422629884928, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1172.4235222180466, "count": 45464, "is_parallel": true, "self": 626.3931424880492, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002515621000043211, "count": 1, "is_parallel": true, "self": 0.0006555900000648762, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018600309999783349, "count": 10, "is_parallel": true, "self": 0.0018600309999783349 } } }, "UnityEnvironment.step": { "total": 0.037510537999992266, "count": 1, "is_parallel": true, "self": 0.0006970779999164733, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000450415000045723, "count": 1, "is_parallel": true, "self": 0.000450415000045723 }, "communicator.exchange": { "total": 0.03444694699999218, "count": 1, "is_parallel": true, "self": 0.03444694699999218 }, "steps_from_proto": { "total": 0.0019160980000378913, "count": 1, "is_parallel": true, "self": 0.00043245999972896243, "children": { "_process_rank_one_or_two_observation": { "total": 0.001483638000308929, "count": 10, "is_parallel": true, "self": 0.001483638000308929 } } } } } } }, "UnityEnvironment.step": { "total": 546.0303797299974, "count": 45463, "is_parallel": true, "self": 26.78007360004426, "children": { "UnityEnvironment._generate_step_input": { "total": 14.418757342982076, "count": 45463, "is_parallel": true, "self": 14.418757342982076 }, "communicator.exchange": { "total": 418.8794542139848, "count": 45463, "is_parallel": true, "self": 418.8794542139848 }, "steps_from_proto": { "total": 85.95209457298631, "count": 45463, "is_parallel": true, "self": 15.225644441087866, "children": { "_process_rank_one_or_two_observation": { "total": 70.72645013189845, "count": 454630, "is_parallel": true, "self": 70.72645013189845 } } } } } } } } } } }, "trainer_advance": { "total": 349.5614038839709, "count": 45464, "self": 1.1470831269866721, "children": { "process_trajectory": { "total": 77.40674663498396, "count": 45464, "self": 75.9997486879837, "children": { "RLTrainer._checkpoint": { "total": 1.4069979470002636, "count": 10, "self": 1.4069979470002636 } } }, "_update_policy": { "total": 271.0075741220003, "count": 113, "self": 150.97261140498563, "children": { "TorchPPOOptimizer.update": { "total": 120.03496271701465, "count": 7680, "self": 120.03496271701465 } } } } } } }, "trainer_threads": { "total": 1.1849997463286854e-06, "count": 1, "self": 1.1849997463286854e-06 }, "TrainerController._save_models": { "total": 0.10835778599994228, "count": 1, "self": 0.0011726339998858748, "children": { "RLTrainer._checkpoint": { "total": 0.1071851520000564, "count": 1, "self": 0.1071851520000564 } } } } } } }