{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0153149366378784, "min": 1.0153149366378784, "max": 2.871737003326416, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9705.3955078125, "min": 9705.3955078125, "max": 29441.046875, "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": 12.056957244873047, "min": 0.4078052043914795, "max": 12.056957244873047, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2351.106689453125, "min": 79.11421203613281, "max": 2423.85986328125, "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": 0.06947603310126235, "min": 0.0633269773288881, "max": 0.07215522509616087, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2779041324050494, "min": 0.2533079093155524, "max": 0.3607761254808044, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18968522829898432, "min": 0.10374271728933843, "max": 0.2743595464556825, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7587409131959373, "min": 0.4149708691573537, "max": 1.288500650840647, "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": 24.181818181818183, "min": 3.1363636363636362, "max": 24.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1064.0, "min": 138.0, "max": 1304.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.181818181818183, "min": 3.1363636363636362, "max": 24.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1064.0, "min": 138.0, "max": 1304.0, "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": "1719298278", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719298709" }, "total": 431.00058207400014, "count": 1, "self": 0.43998622000015075, "children": { "run_training.setup": { "total": 0.061729205000006004, "count": 1, "self": 0.061729205000006004 }, "TrainerController.start_learning": { "total": 430.498866649, "count": 1, "self": 0.5462169530345591, "children": { "TrainerController._reset_env": { "total": 3.502513629999953, "count": 1, "self": 3.502513629999953 }, "TrainerController.advance": { "total": 426.3576109659656, "count": 18201, "self": 0.25000128397721255, "children": { "env_step": { "total": 426.1076096819884, "count": 18201, "self": 274.4657257749915, "children": { "SubprocessEnvManager._take_step": { "total": 151.37669641200068, "count": 18201, "self": 1.3952502450015345, "children": { "TorchPolicy.evaluate": { "total": 149.98144616699915, "count": 18201, "self": 149.98144616699915 } } }, "workers": { "total": 0.2651874949962121, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 429.3775425950146, "count": 18201, "is_parallel": true, "self": 217.78812649303245, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006718633999980739, "count": 1, "is_parallel": true, "self": 0.005078430000367007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016402039996137319, "count": 10, "is_parallel": true, "self": 0.0016402039996137319 } } }, "UnityEnvironment.step": { "total": 0.03606019300002572, "count": 1, "is_parallel": true, "self": 0.0006216059999815116, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004252670000823855, "count": 1, "is_parallel": true, "self": 0.0004252670000823855 }, "communicator.exchange": { "total": 0.03313674899993657, "count": 1, "is_parallel": true, "self": 0.03313674899993657 }, "steps_from_proto": { "total": 0.0018765710000252511, "count": 1, "is_parallel": true, "self": 0.0003883579998955611, "children": { "_process_rank_one_or_two_observation": { "total": 0.00148821300012969, "count": 10, "is_parallel": true, "self": 0.00148821300012969 } } } } } } }, "UnityEnvironment.step": { "total": 211.58941610198212, "count": 18200, "is_parallel": true, "self": 9.72757870299506, "children": { "UnityEnvironment._generate_step_input": { "total": 5.165087861010193, "count": 18200, "is_parallel": true, "self": 5.165087861010193 }, "communicator.exchange": { "total": 165.09208939298549, "count": 18200, "is_parallel": true, "self": 165.09208939298549 }, "steps_from_proto": { "total": 31.604660144991385, "count": 18200, "is_parallel": true, "self": 5.840813084941715, "children": { "_process_rank_one_or_two_observation": { "total": 25.76384706004967, "count": 182000, "is_parallel": true, "self": 25.76384706004967 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001663559999087738, "count": 1, "self": 0.0001663559999087738, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 421.33016167194035, "count": 648197, "is_parallel": true, "self": 13.24267909199375, "children": { "process_trajectory": { "total": 232.60717383394604, "count": 648197, "is_parallel": true, "self": 231.97582495894608, "children": { "RLTrainer._checkpoint": { "total": 0.6313488749999578, "count": 4, "is_parallel": true, "self": 0.6313488749999578 } } }, "_update_policy": { "total": 175.48030874600056, "count": 90, "is_parallel": true, "self": 53.92280309499836, "children": { "TorchPPOOptimizer.update": { "total": 121.5575056510022, "count": 4587, "is_parallel": true, "self": 121.5575056510022 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09235874399996646, "count": 1, "self": 0.0009444269999221433, "children": { "RLTrainer._checkpoint": { "total": 0.09141431700004432, "count": 1, "self": 0.09141431700004432 } } } } } } }