{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.852093517780304, "min": 0.8313882946968079, "max": 2.8371405601501465, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8098.296875, "min": 8098.296875, "max": 28961.53125, "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": 12.88045597076416, "min": 0.3220067322254181, "max": 12.977343559265137, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.68896484375, "min": 62.46930694580078, "max": 2660.35546875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07234634406403548, "min": 0.06324103302807392, "max": 0.07615671012172243, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2893853762561419, "min": 0.2549555984390763, "max": 0.3504821424310863, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20953501848613515, "min": 0.14811682490421935, "max": 0.26572960936555673, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8381400739445406, "min": 0.5924672996168774, "max": 1.2591190767638825, "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": 25.022727272727273, "min": 3.7045454545454546, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 163.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 3.7045454545454546, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 163.0, "max": 1391.0, "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": "1743968604", "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": "1743969045" }, "total": 440.347186009, "count": 1, "self": 0.7879881480000677, "children": { "run_training.setup": { "total": 0.023761057999990953, "count": 1, "self": 0.023761057999990953 }, "TrainerController.start_learning": { "total": 439.5354368029999, "count": 1, "self": 0.366101315991159, "children": { "TrainerController._reset_env": { "total": 3.209476676999998, "count": 1, "self": 3.209476676999998 }, "TrainerController.advance": { "total": 435.8234109080089, "count": 18192, "self": 0.3844567800168761, "children": { "env_step": { "total": 310.98025275498844, "count": 18192, "self": 236.33930928800203, "children": { "SubprocessEnvManager._take_step": { "total": 74.42871971898262, "count": 18192, "self": 1.3132103789940857, "children": { "TorchPolicy.evaluate": { "total": 73.11550933998853, "count": 18192, "self": 73.11550933998853 } } }, "workers": { "total": 0.21222374800379384, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 437.87587649700424, "count": 18192, "is_parallel": true, "self": 230.84684459901223, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006355127999995602, "count": 1, "is_parallel": true, "self": 0.004674289000263343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016808389997322593, "count": 10, "is_parallel": true, "self": 0.0016808389997322593 } } }, "UnityEnvironment.step": { "total": 0.058821697999974276, "count": 1, "is_parallel": true, "self": 0.00055536000002121, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037637399998402543, "count": 1, "is_parallel": true, "self": 0.00037637399998402543 }, "communicator.exchange": { "total": 0.05605767899999137, "count": 1, "is_parallel": true, "self": 0.05605767899999137 }, "steps_from_proto": { "total": 0.0018322849999776736, "count": 1, "is_parallel": true, "self": 0.00034177899999576766, "children": { "_process_rank_one_or_two_observation": { "total": 0.001490505999981906, "count": 10, "is_parallel": true, "self": 0.001490505999981906 } } } } } } }, "UnityEnvironment.step": { "total": 207.029031897992, "count": 18191, "is_parallel": true, "self": 9.96113786299145, "children": { "UnityEnvironment._generate_step_input": { "total": 5.503942356996731, "count": 18191, "is_parallel": true, "self": 5.503942356996731 }, "communicator.exchange": { "total": 158.67342102499333, "count": 18191, "is_parallel": true, "self": 158.67342102499333 }, "steps_from_proto": { "total": 32.8905306530105, "count": 18191, "is_parallel": true, "self": 5.944594386991412, "children": { "_process_rank_one_or_two_observation": { "total": 26.94593626601909, "count": 181910, "is_parallel": true, "self": 26.94593626601909 } } } } } } } } } } }, "trainer_advance": { "total": 124.45870137300358, "count": 18192, "self": 0.4619072139820446, "children": { "process_trajectory": { "total": 27.943587980022016, "count": 18192, "self": 27.452052090021994, "children": { "RLTrainer._checkpoint": { "total": 0.49153589000002285, "count": 4, "self": 0.49153589000002285 } } }, "_update_policy": { "total": 96.05320617899952, "count": 90, "self": 38.94768425200675, "children": { "TorchPPOOptimizer.update": { "total": 57.105521926992765, "count": 4587, "self": 57.105521926992765 } } } } } } }, "trainer_threads": { "total": 1.089000079446123e-06, "count": 1, "self": 1.089000079446123e-06 }, "TrainerController._save_models": { "total": 0.1364468129997931, "count": 1, "self": 0.0013576329997704306, "children": { "RLTrainer._checkpoint": { "total": 0.13508918000002268, "count": 1, "self": 0.13508918000002268 } } } } } } }