{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9106971621513367, "min": 0.8602818250656128, "max": 2.8318519592285156, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8655.265625, "min": 8655.265625, "max": 28907.544921875, "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": 11.955513000488281, "min": 0.5082069635391235, "max": 11.955513000488281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2331.324951171875, "min": 98.59214782714844, "max": 2431.02978515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06882720557262598, "min": 0.058344140968413324, "max": 0.07504609338431299, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2753088222905039, "min": 0.2333765638736533, "max": 0.37175043071291675, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19187686263638384, "min": 0.14080628223589384, "max": 0.2791702730982911, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7675074505455354, "min": 0.5632251289435753, "max": 1.3958513654914557, "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.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.Environment.CumulativeReward.mean": { "value": 23.727272727272727, "min": 3.977272727272727, "max": 23.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1044.0, "min": 175.0, "max": 1301.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.727272727272727, "min": 3.977272727272727, "max": 23.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1044.0, "min": 175.0, "max": 1301.0, "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": "1739102836", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739103257" }, "total": 421.2740359690001, "count": 1, "self": 0.4397528910001256, "children": { "run_training.setup": { "total": 0.023113243000125294, "count": 1, "self": 0.023113243000125294 }, "TrainerController.start_learning": { "total": 420.8111698349999, "count": 1, "self": 0.317373799998677, "children": { "TrainerController._reset_env": { "total": 3.390884405999941, "count": 1, "self": 3.390884405999941 }, "TrainerController.advance": { "total": 417.0162737450012, "count": 18192, "self": 0.32890648099350983, "children": { "env_step": { "total": 291.66436108100197, "count": 18192, "self": 221.73423482998373, "children": { "SubprocessEnvManager._take_step": { "total": 69.73403730201039, "count": 18192, "self": 1.182485461019951, "children": { "TorchPolicy.evaluate": { "total": 68.55155184099044, "count": 18192, "self": 68.55155184099044 } } }, "workers": { "total": 0.19608894900784435, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 419.3261528479886, "count": 18192, "is_parallel": true, "self": 224.39912378698364, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00546928099993238, "count": 1, "is_parallel": true, "self": 0.004133423999974184, "children": { "_process_rank_one_or_two_observation": { "total": 0.001335856999958196, "count": 10, "is_parallel": true, "self": 0.001335856999958196 } } }, "UnityEnvironment.step": { "total": 0.06369104400005199, "count": 1, "is_parallel": true, "self": 0.0005540530000871513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003744789999018394, "count": 1, "is_parallel": true, "self": 0.0003744789999018394 }, "communicator.exchange": { "total": 0.06095508700013852, "count": 1, "is_parallel": true, "self": 0.06095508700013852 }, "steps_from_proto": { "total": 0.0018074249999244785, "count": 1, "is_parallel": true, "self": 0.0003428750001148728, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014645499998096057, "count": 10, "is_parallel": true, "self": 0.0014645499998096057 } } } } } } }, "UnityEnvironment.step": { "total": 194.927029061005, "count": 18191, "is_parallel": true, "self": 9.3430127589952, "children": { "UnityEnvironment._generate_step_input": { "total": 5.290888481987622, "count": 18191, "is_parallel": true, "self": 5.290888481987622 }, "communicator.exchange": { "total": 150.2689711730102, "count": 18191, "is_parallel": true, "self": 150.2689711730102 }, "steps_from_proto": { "total": 30.024156647011978, "count": 18191, "is_parallel": true, "self": 5.244265954092043, "children": { "_process_rank_one_or_two_observation": { "total": 24.779890692919935, "count": 181910, "is_parallel": true, "self": 24.779890692919935 } } } } } } } } } } }, "trainer_advance": { "total": 125.02300618300569, "count": 18192, "self": 0.37748005898811243, "children": { "process_trajectory": { "total": 26.89845201801677, "count": 18192, "self": 26.31206522801699, "children": { "RLTrainer._checkpoint": { "total": 0.5863867899997786, "count": 4, "self": 0.5863867899997786 } } }, "_update_policy": { "total": 97.74707410600081, "count": 90, "self": 39.81941510300703, "children": { "TorchPPOOptimizer.update": { "total": 57.92765900299378, "count": 4587, "self": 57.92765900299378 } } } } } } }, "trainer_threads": { "total": 9.499999578110874e-07, "count": 1, "self": 9.499999578110874e-07 }, "TrainerController._save_models": { "total": 0.08663693400012562, "count": 1, "self": 0.0008800989999144804, "children": { "RLTrainer._checkpoint": { "total": 0.08575683500021114, "count": 1, "self": 0.08575683500021114 } } } } } } }