{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8827674984931946, "min": 0.8827674984931946, "max": 2.857097864151001, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8389.822265625, "min": 8389.822265625, "max": 29165.25390625, "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": 13.031387329101562, "min": 0.5609398484230042, "max": 13.09267520904541, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2541.12060546875, "min": 108.82233428955078, "max": 2670.90576171875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07493663893052928, "min": 0.062107337467308496, "max": 0.07663156105677355, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2997465557221171, "min": 0.2527969093952218, "max": 0.3705257126792133, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18633273236599623, "min": 0.12818747937140584, "max": 0.29279474979814357, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7453309294639849, "min": 0.5127499174856234, "max": 1.394047214996581, "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": 25.431818181818183, "min": 3.4318181818181817, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 151.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.4318181818181817, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 151.0, "max": 1402.0, "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": "1792869795", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1792870202" }, "total": 406.679251477, "count": 1, "self": 0.32151323300013246, "children": { "run_training.setup": { "total": 0.026950936999810438, "count": 1, "self": 0.026950936999810438 }, "TrainerController.start_learning": { "total": 406.33078730700004, "count": 1, "self": 0.4577259590009817, "children": { "TrainerController._reset_env": { "total": 2.089654481000025, "count": 1, "self": 2.089654481000025 }, "TrainerController.advance": { "total": 403.703954272999, "count": 18192, "self": 0.42866826000749825, "children": { "env_step": { "total": 288.8224787839938, "count": 18192, "self": 215.83430546997374, "children": { "SubprocessEnvManager._take_step": { "total": 72.71484767301422, "count": 18192, "self": 1.4607823310232106, "children": { "TorchPolicy.evaluate": { "total": 71.25406534199101, "count": 18192, "self": 71.25406534199101 } } }, "workers": { "total": 0.2733256410058402, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 405.38776821099395, "count": 18192, "is_parallel": true, "self": 217.359221095983, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002061776999880749, "count": 1, "is_parallel": true, "self": 0.0006367410001075768, "children": { "_process_rank_one_or_two_observation": { "total": 0.001425035999773172, "count": 10, "is_parallel": true, "self": 0.001425035999773172 } } }, "UnityEnvironment.step": { "total": 0.030390099999976883, "count": 1, "is_parallel": true, "self": 0.0004935619997468166, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002779250000912725, "count": 1, "is_parallel": true, "self": 0.0002779250000912725 }, "communicator.exchange": { "total": 0.02837921900004403, "count": 1, "is_parallel": true, "self": 0.02837921900004403 }, "steps_from_proto": { "total": 0.0012393940000947623, "count": 1, "is_parallel": true, "self": 0.0002573500000835338, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009820440000112285, "count": 10, "is_parallel": true, "self": 0.0009820440000112285 } } } } } } }, "UnityEnvironment.step": { "total": 188.02854711501095, "count": 18191, "is_parallel": true, "self": 6.841138840028407, "children": { "UnityEnvironment._generate_step_input": { "total": 3.662293637017001, "count": 18191, "is_parallel": true, "self": 3.662293637017001 }, "communicator.exchange": { "total": 156.7319673339764, "count": 18191, "is_parallel": true, "self": 156.7319673339764 }, "steps_from_proto": { "total": 20.793147303989144, "count": 18191, "is_parallel": true, "self": 4.157326524933524, "children": { "_process_rank_one_or_two_observation": { "total": 16.63582077905562, "count": 181910, "is_parallel": true, "self": 16.63582077905562 } } } } } } } } } } }, "trainer_advance": { "total": 114.4528072289977, "count": 18192, "self": 0.6242806449806722, "children": { "process_trajectory": { "total": 23.037981732017897, "count": 18192, "self": 22.68273565801769, "children": { "RLTrainer._checkpoint": { "total": 0.35524607400020614, "count": 4, "self": 0.35524607400020614 } } }, "_update_policy": { "total": 90.79054485199913, "count": 90, "self": 36.366922234994036, "children": { "TorchPPOOptimizer.update": { "total": 54.423622617005094, "count": 4587, "self": 54.423622617005094 } } } } } } }, "trainer_threads": { "total": 1.0429998837935273e-06, "count": 1, "self": 1.0429998837935273e-06 }, "TrainerController._save_models": { "total": 0.07945155100014745, "count": 1, "self": 0.0007381760001408111, "children": { "RLTrainer._checkpoint": { "total": 0.07871337500000664, "count": 1, "self": 0.07871337500000664 } } } } } } }