{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7740551233291626, "min": 0.7730932235717773, "max": 2.8372554779052734, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7356.61962890625, "min": 7356.61962890625, "max": 28962.703125, "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": 13.02734088897705, "min": 0.41042274236679077, "max": 13.02734088897705, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.33154296875, "min": 79.62200927734375, "max": 2650.6767578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.101150900792181, "min": 0.09373601831783376, "max": 0.10277270829644347, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.404603603168724, "min": 0.3802865994004213, "max": 0.5138635414822174, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2043496016595586, "min": 0.11527159011497234, "max": 0.27423359815250425, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8173984066382344, "min": 0.4610863604598894, "max": 1.25942898483253, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "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": 25.65909090909091, "min": 3.340909090909091, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 147.0, "max": 1420.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 3.340909090909091, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 147.0, "max": 1420.0, "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": "1739878091", "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": "1739878573" }, "total": 482.154772243, "count": 1, "self": 0.7517600840001251, "children": { "run_training.setup": { "total": 0.023518303999935597, "count": 1, "self": 0.023518303999935597 }, "TrainerController.start_learning": { "total": 481.37949385499996, "count": 1, "self": 0.3728264659898741, "children": { "TrainerController._reset_env": { "total": 3.2119858529999874, "count": 1, "self": 3.2119858529999874 }, "TrainerController.advance": { "total": 477.66402210101023, "count": 18192, "self": 0.3624904570106082, "children": { "env_step": { "total": 298.6962199630145, "count": 18192, "self": 226.2206120640435, "children": { "SubprocessEnvManager._take_step": { "total": 72.25962844198807, "count": 18192, "self": 1.246361858992941, "children": { "TorchPolicy.evaluate": { "total": 71.01326658299513, "count": 18192, "self": 71.01326658299513 } } }, "workers": { "total": 0.21597945698295007, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 479.8521826609924, "count": 18192, "is_parallel": true, "self": 281.75526081197677, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005997724000053495, "count": 1, "is_parallel": true, "self": 0.0043738780000239785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016238460000295163, "count": 10, "is_parallel": true, "self": 0.0016238460000295163 } } }, "UnityEnvironment.step": { "total": 0.04395548100001179, "count": 1, "is_parallel": true, "self": 0.0006084840001676639, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039963599988368514, "count": 1, "is_parallel": true, "self": 0.00039963599988368514 }, "communicator.exchange": { "total": 0.04111294399990584, "count": 1, "is_parallel": true, "self": 0.04111294399990584 }, "steps_from_proto": { "total": 0.0018344170000546, "count": 1, "is_parallel": true, "self": 0.00032962999944174953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015047870006128505, "count": 10, "is_parallel": true, "self": 0.0015047870006128505 } } } } } } }, "UnityEnvironment.step": { "total": 198.09692184901564, "count": 18191, "is_parallel": true, "self": 9.597537127012629, "children": { "UnityEnvironment._generate_step_input": { "total": 5.184328476025485, "count": 18191, "is_parallel": true, "self": 5.184328476025485 }, "communicator.exchange": { "total": 152.76287805698075, "count": 18191, "is_parallel": true, "self": 152.76287805698075 }, "steps_from_proto": { "total": 30.552178188996777, "count": 18191, "is_parallel": true, "self": 5.453911055014032, "children": { "_process_rank_one_or_two_observation": { "total": 25.098267133982745, "count": 181910, "is_parallel": true, "self": 25.098267133982745 } } } } } } } } } } }, "trainer_advance": { "total": 178.6053116809851, "count": 18192, "self": 0.4554956390031748, "children": { "process_trajectory": { "total": 26.797175010982755, "count": 18192, "self": 26.33430542598262, "children": { "RLTrainer._checkpoint": { "total": 0.462869585000135, "count": 4, "self": 0.462869585000135 } } }, "_update_policy": { "total": 151.35264103099917, "count": 90, "self": 39.94573282600368, "children": { "TorchPPOOptimizer.update": { "total": 111.40690820499549, "count": 9177, "self": 111.40690820499549 } } } } } } }, "trainer_threads": { "total": 1.1839999842777615e-06, "count": 1, "self": 1.1839999842777615e-06 }, "TrainerController._save_models": { "total": 0.13065825099988615, "count": 1, "self": 0.002564974999813785, "children": { "RLTrainer._checkpoint": { "total": 0.12809327600007236, "count": 1, "self": 0.12809327600007236 } } } } } } }