{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8407251834869385, "min": 0.8407251834869385, "max": 2.8688902854919434, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8045.740234375, "min": 8045.740234375, "max": 29538.09375, "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": 12.960145950317383, "min": 0.3390136659145355, "max": 12.960145950317383, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2527.228515625, "min": 65.7686538696289, "max": 2635.49755859375, "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": 0.06481352740842804, "min": 0.06363655460454003, "max": 0.07535808433963478, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25925410963371215, "min": 0.2590154244395557, "max": 0.372909425648258, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20023177538578416, "min": 0.09746791912338643, "max": 0.2810297635256075, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8009271015431366, "min": 0.3898716764935457, "max": 1.4051488176280376, "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": 24.931818181818183, "min": 2.75, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 121.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 2.75, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 121.0, "max": 1415.0, "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": "1731301850", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731302440" }, "total": 589.968594878, "count": 1, "self": 0.5381730819999575, "children": { "run_training.setup": { "total": 0.06999094399998285, "count": 1, "self": 0.06999094399998285 }, "TrainerController.start_learning": { "total": 589.360430852, "count": 1, "self": 0.8702333999985967, "children": { "TrainerController._reset_env": { "total": 6.334696660999953, "count": 1, "self": 6.334696660999953 }, "TrainerController.advance": { "total": 582.0694511580014, "count": 18203, "self": 0.4153701610209737, "children": { "env_step": { "total": 581.6540809969804, "count": 18203, "self": 446.2179588109723, "children": { "SubprocessEnvManager._take_step": { "total": 135.01991319600643, "count": 18203, "self": 2.2349506340045764, "children": { "TorchPolicy.evaluate": { "total": 132.78496256200185, "count": 18203, "self": 132.78496256200185 } } }, "workers": { "total": 0.4162089900016781, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 587.4720408889999, "count": 18203, "is_parallel": true, "self": 282.82053505199485, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00260218099992926, "count": 1, "is_parallel": true, "self": 0.0007787229999394185, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018234579999898415, "count": 10, "is_parallel": true, "self": 0.0018234579999898415 } } }, "UnityEnvironment.step": { "total": 0.07912608599997384, "count": 1, "is_parallel": true, "self": 0.0008318790000885201, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046831499992094905, "count": 1, "is_parallel": true, "self": 0.00046831499992094905 }, "communicator.exchange": { "total": 0.0756912319999401, "count": 1, "is_parallel": true, "self": 0.0756912319999401 }, "steps_from_proto": { "total": 0.002134660000024269, "count": 1, "is_parallel": true, "self": 0.0003885920000357146, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017460679999885542, "count": 10, "is_parallel": true, "self": 0.0017460679999885542 } } } } } } }, "UnityEnvironment.step": { "total": 304.65150583700506, "count": 18202, "is_parallel": true, "self": 14.513723578006307, "children": { "UnityEnvironment._generate_step_input": { "total": 7.387946464996617, "count": 18202, "is_parallel": true, "self": 7.387946464996617 }, "communicator.exchange": { "total": 240.13879461600493, "count": 18202, "is_parallel": true, "self": 240.13879461600493 }, "steps_from_proto": { "total": 42.61104117799721, "count": 18202, "is_parallel": true, "self": 8.366737995043195, "children": { "_process_rank_one_or_two_observation": { "total": 34.24430318295401, "count": 182020, "is_parallel": true, "self": 34.24430318295401 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00025616700008868065, "count": 1, "self": 0.00025616700008868065, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 575.207753723995, "count": 771523, "is_parallel": true, "self": 17.48773324204626, "children": { "process_trajectory": { "total": 307.15225774794885, "count": 771523, "is_parallel": true, "self": 305.80817943894886, "children": { "RLTrainer._checkpoint": { "total": 1.3440783089999968, "count": 4, "is_parallel": true, "self": 1.3440783089999968 } } }, "_update_policy": { "total": 250.56776273399987, "count": 90, "is_parallel": true, "self": 68.63278823100018, "children": { "TorchPPOOptimizer.update": { "total": 181.9349745029997, "count": 4587, "is_parallel": true, "self": 181.9349745029997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08579346600004101, "count": 1, "self": 0.003150736999941728, "children": { "RLTrainer._checkpoint": { "total": 0.08264272900009928, "count": 1, "self": 0.08264272900009928 } } } } } } }