{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8373638391494751, "min": 0.835953414440155, "max": 2.8695268630981445, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7958.3056640625, "min": 7958.3056640625, "max": 29292.130859375, "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": 12.810797691345215, "min": 0.4701075553894043, "max": 12.812806129455566, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2498.10546875, "min": 91.20086669921875, "max": 2613.8125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07102309162291931, "min": 0.06121451833671159, "max": 0.07728030841270297, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28409236649167724, "min": 0.24485807334684637, "max": 0.358896903063093, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20026675882000547, "min": 0.16621195433853084, "max": 0.2843870248280319, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8010670352800219, "min": 0.6648478173541233, "max": 1.4219351241401597, "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": 25.636363636363637, "min": 4.136363636363637, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 182.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 4.136363636363637, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 182.0, "max": 1393.0, "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": "1775900082", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1775900571" }, "total": 489.2244507989999, "count": 1, "self": 0.6904084430000239, "children": { "run_training.setup": { "total": 0.02289387199994053, "count": 1, "self": 0.02289387199994053 }, "TrainerController.start_learning": { "total": 488.51114848399993, "count": 1, "self": 0.41939719798847364, "children": { "TrainerController._reset_env": { "total": 3.531503165999993, "count": 1, "self": 3.531503165999993 }, "TrainerController.advance": { "total": 484.4217918100114, "count": 18192, "self": 0.43492603908407546, "children": { "env_step": { "total": 354.6724421249512, "count": 18192, "self": 275.98710868093144, "children": { "SubprocessEnvManager._take_step": { "total": 78.43423929503547, "count": 18192, "self": 1.3932146300167005, "children": { "TorchPolicy.evaluate": { "total": 77.04102466501877, "count": 18192, "self": 77.04102466501877 } } }, "workers": { "total": 0.2510941489842935, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 486.2859603130016, "count": 18192, "is_parallel": true, "self": 244.07059676405015, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005018960999905175, "count": 1, "is_parallel": true, "self": 0.0036446730000534444, "children": { "_process_rank_one_or_two_observation": { "total": 0.001374287999851731, "count": 10, "is_parallel": true, "self": 0.001374287999851731 } } }, "UnityEnvironment.step": { "total": 0.03845664100003887, "count": 1, "is_parallel": true, "self": 0.0006099380000250676, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040290699985234824, "count": 1, "is_parallel": true, "self": 0.00040290699985234824 }, "communicator.exchange": { "total": 0.03544487800013485, "count": 1, "is_parallel": true, "self": 0.03544487800013485 }, "steps_from_proto": { "total": 0.001998918000026606, "count": 1, "is_parallel": true, "self": 0.00039459399999941525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016043240000271908, "count": 10, "is_parallel": true, "self": 0.0016043240000271908 } } } } } } }, "UnityEnvironment.step": { "total": 242.21536354895147, "count": 18191, "is_parallel": true, "self": 11.064091406958823, "children": { "UnityEnvironment._generate_step_input": { "total": 5.994486384975517, "count": 18191, "is_parallel": true, "self": 5.994486384975517 }, "communicator.exchange": { "total": 184.3977055750538, "count": 18191, "is_parallel": true, "self": 184.3977055750538 }, "steps_from_proto": { "total": 40.75908018196333, "count": 18191, "is_parallel": true, "self": 7.19158117986899, "children": { "_process_rank_one_or_two_observation": { "total": 33.56749900209434, "count": 181910, "is_parallel": true, "self": 33.56749900209434 } } } } } } } } } } }, "trainer_advance": { "total": 129.31442364597615, "count": 18192, "self": 0.5330680419692726, "children": { "process_trajectory": { "total": 28.932554999006697, "count": 18192, "self": 28.466814559006707, "children": { "RLTrainer._checkpoint": { "total": 0.4657404399999905, "count": 4, "self": 0.4657404399999905 } } }, "_update_policy": { "total": 99.84880060500018, "count": 90, "self": 40.22903400601035, "children": { "TorchPPOOptimizer.update": { "total": 59.61976659898983, "count": 4587, "self": 59.61976659898983 } } } } } } }, "trainer_threads": { "total": 1.5870000424911268e-06, "count": 1, "self": 1.5870000424911268e-06 }, "TrainerController._save_models": { "total": 0.13845472299999528, "count": 1, "self": 0.001020617999984097, "children": { "RLTrainer._checkpoint": { "total": 0.1374341050000112, "count": 1, "self": 0.1374341050000112 } } } } } } }