{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8789896965026855, "min": 0.8789896965026855, "max": 2.8691322803497314, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8402.2626953125, "min": 8402.2626953125, "max": 29414.34375, "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": 12.624608039855957, "min": 0.4429478943347931, "max": 12.624608039855957, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2461.798583984375, "min": 85.93189239501953, "max": 2552.21337890625, "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": 0.06779338822240129, "min": 0.05930634795458231, "max": 0.07584754020448975, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27117355288960515, "min": 0.23722539181832925, "max": 0.3559574342220645, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20739913855989772, "min": 0.12902782990953282, "max": 0.2976035281431441, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8295965542395909, "min": 0.5161113196381313, "max": 1.424557031077497, "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": 24.818181818181817, "min": 3.6136363636363638, "max": 24.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1092.0, "min": 159.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.818181818181817, "min": 3.6136363636363638, "max": 24.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1092.0, "min": 159.0, "max": 1360.0, "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": "1712024455", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712024994" }, "total": 538.2422409879999, "count": 1, "self": 0.4851062870000078, "children": { "run_training.setup": { "total": 0.0895506069999783, "count": 1, "self": 0.0895506069999783 }, "TrainerController.start_learning": { "total": 537.667584094, "count": 1, "self": 0.7457198189944165, "children": { "TrainerController._reset_env": { "total": 3.6023299940000015, "count": 1, "self": 3.6023299940000015 }, "TrainerController.advance": { "total": 533.2119446540054, "count": 18201, "self": 0.37098912402086626, "children": { "env_step": { "total": 532.8409555299845, "count": 18201, "self": 350.187060171989, "children": { "SubprocessEnvManager._take_step": { "total": 182.28480265299635, "count": 18201, "self": 1.8520974959961904, "children": { "TorchPolicy.evaluate": { "total": 180.43270515700016, "count": 18201, "self": 180.43270515700016 } } }, "workers": { "total": 0.36909270499916147, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 536.0784766660139, "count": 18201, "is_parallel": true, "self": 260.6579774290284, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0070936469999764995, "count": 1, "is_parallel": true, "self": 0.004353646000026856, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027400009999496433, "count": 10, "is_parallel": true, "self": 0.0027400009999496433 } } }, "UnityEnvironment.step": { "total": 0.04137272299999495, "count": 1, "is_parallel": true, "self": 0.0008185930000195185, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004334289999974317, "count": 1, "is_parallel": true, "self": 0.0004334289999974317 }, "communicator.exchange": { "total": 0.03793635799996764, "count": 1, "is_parallel": true, "self": 0.03793635799996764 }, "steps_from_proto": { "total": 0.002184343000010358, "count": 1, "is_parallel": true, "self": 0.00042634100003624553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017580019999741126, "count": 10, "is_parallel": true, "self": 0.0017580019999741126 } } } } } } }, "UnityEnvironment.step": { "total": 275.4204992369855, "count": 18200, "is_parallel": true, "self": 12.693510673982985, "children": { "UnityEnvironment._generate_step_input": { "total": 6.38254840700273, "count": 18200, "is_parallel": true, "self": 6.38254840700273 }, "communicator.exchange": { "total": 216.26516267799985, "count": 18200, "is_parallel": true, "self": 216.26516267799985 }, "steps_from_proto": { "total": 40.07927747799994, "count": 18200, "is_parallel": true, "self": 7.80722509198489, "children": { "_process_rank_one_or_two_observation": { "total": 32.27205238601505, "count": 182000, "is_parallel": true, "self": 32.27205238601505 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015272500013452373, "count": 1, "self": 0.00015272500013452373, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 526.0710967579818, "count": 794421, "is_parallel": true, "self": 17.970930558036628, "children": { "process_trajectory": { "total": 293.8626648639451, "count": 794421, "is_parallel": true, "self": 292.7537404669452, "children": { "RLTrainer._checkpoint": { "total": 1.108924396999896, "count": 4, "is_parallel": true, "self": 1.108924396999896 } } }, "_update_policy": { "total": 214.23750133600004, "count": 90, "is_parallel": true, "self": 59.28867317099673, "children": { "TorchPPOOptimizer.update": { "total": 154.9488281650033, "count": 4587, "is_parallel": true, "self": 154.9488281650033 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10743690200001765, "count": 1, "self": 0.0011553150000054302, "children": { "RLTrainer._checkpoint": { "total": 0.10628158700001222, "count": 1, "self": 0.10628158700001222 } } } } } } }