{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9962137341499329, "min": 0.9950190186500549, "max": 2.86851167678833, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9533.765625, "min": 9533.765625, "max": 29439.53515625, "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": 12.907429695129395, "min": 0.40943893790245056, "max": 12.907429695129395, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.94873046875, "min": 79.43115234375, "max": 2620.5478515625, "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": 0.06699768759826125, "min": 0.06071819750895706, "max": 0.07602247710451147, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.267990750393045, "min": 0.26057634065135993, "max": 0.37829495221476284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20520784771617723, "min": 0.12975001794185637, "max": 0.29191491364264016, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8208313908647089, "min": 0.5190000717674255, "max": 1.4595745682132009, "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": 25.454545454545453, "min": 3.5681818181818183, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 157.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.5681818181818183, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 157.0, "max": 1394.0, "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": "1690308765", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690309226" }, "total": 461.928468864, "count": 1, "self": 0.3852304750000144, "children": { "run_training.setup": { "total": 0.03338397600003873, "count": 1, "self": 0.03338397600003873 }, "TrainerController.start_learning": { "total": 461.50985441299997, "count": 1, "self": 0.5494176310052126, "children": { "TrainerController._reset_env": { "total": 6.227949724000041, "count": 1, "self": 6.227949724000041 }, "TrainerController.advance": { "total": 454.58739936799475, "count": 18203, "self": 0.2528142130012725, "children": { "env_step": { "total": 454.3345851549935, "count": 18203, "self": 329.26153519999, "children": { "SubprocessEnvManager._take_step": { "total": 124.80379151399995, "count": 18203, "self": 1.7186716840042777, "children": { "TorchPolicy.evaluate": { "total": 123.08511982999568, "count": 18203, "self": 123.08511982999568 } } }, "workers": { "total": 0.26925844100350105, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 460.10594109899574, "count": 18203, "is_parallel": true, "self": 221.32011217599523, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006090288999985205, "count": 1, "is_parallel": true, "self": 0.0038651980000281583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022250909999570467, "count": 10, "is_parallel": true, "self": 0.0022250909999570467 } } }, "UnityEnvironment.step": { "total": 0.049688754999976936, "count": 1, "is_parallel": true, "self": 0.0006812820000163811, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004827079999927264, "count": 1, "is_parallel": true, "self": 0.0004827079999927264 }, "communicator.exchange": { "total": 0.04603659399998605, "count": 1, "is_parallel": true, "self": 0.04603659399998605 }, "steps_from_proto": { "total": 0.002488170999981776, "count": 1, "is_parallel": true, "self": 0.00042775600002187275, "children": { "_process_rank_one_or_two_observation": { "total": 0.002060414999959903, "count": 10, "is_parallel": true, "self": 0.002060414999959903 } } } } } } }, "UnityEnvironment.step": { "total": 238.7858289230005, "count": 18202, "is_parallel": true, "self": 10.349847487992065, "children": { "UnityEnvironment._generate_step_input": { "total": 5.087651305996417, "count": 18202, "is_parallel": true, "self": 5.087651305996417 }, "communicator.exchange": { "total": 189.45999052001133, "count": 18202, "is_parallel": true, "self": 189.45999052001133 }, "steps_from_proto": { "total": 33.888339609000695, "count": 18202, "is_parallel": true, "self": 6.226332939011911, "children": { "_process_rank_one_or_two_observation": { "total": 27.662006669988784, "count": 182020, "is_parallel": true, "self": 27.662006669988784 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016128000004300702, "count": 1, "self": 0.00016128000004300702, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.79781990600515, "count": 429343, "is_parallel": true, "self": 9.886641140016707, "children": { "process_trajectory": { "total": 245.97935274298874, "count": 429343, "is_parallel": true, "self": 245.21461468298872, "children": { "RLTrainer._checkpoint": { "total": 0.7647380600000133, "count": 4, "is_parallel": true, "self": 0.7647380600000133 } } }, "_update_policy": { "total": 194.9318260229997, "count": 90, "is_parallel": true, "self": 76.77702708099736, "children": { "TorchPPOOptimizer.update": { "total": 118.15479894200234, "count": 4587, "is_parallel": true, "self": 118.15479894200234 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14492640999992545, "count": 1, "self": 0.0008488729999953648, "children": { "RLTrainer._checkpoint": { "total": 0.1440775369999301, "count": 1, "self": 0.1440775369999301 } } } } } } }