{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8374715447425842, "min": 0.8374715447425842, "max": 2.8478808403015137, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7959.32958984375, "min": 7959.32958984375, "max": 29071.16796875, "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": 12.87462329864502, "min": 0.530041515827179, "max": 12.87462329864502, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2510.551513671875, "min": 102.82804870605469, "max": 2609.01611328125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07039026949275343, "min": 0.06246788312644497, "max": 0.0753445921491577, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2815610779710137, "min": 0.2619078407799095, "max": 0.3638571942996635, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18482615564968072, "min": 0.14283845720095925, "max": 0.2994278641600235, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7393046225987229, "min": 0.571353828803837, "max": 1.3523941653616287, "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": 25.568181818181817, "min": 4.090909090909091, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 180.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 4.090909090909091, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 180.0, "max": 1397.0, "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": "1779569103", "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": "1779569568" }, "total": 465.0945060910001, "count": 1, "self": 0.7490702310001325, "children": { "run_training.setup": { "total": 0.02636373099994671, "count": 1, "self": 0.02636373099994671 }, "TrainerController.start_learning": { "total": 464.319072129, "count": 1, "self": 0.36035243301034825, "children": { "TrainerController._reset_env": { "total": 3.242070492000039, "count": 1, "self": 3.242070492000039 }, "TrainerController.advance": { "total": 460.5964654119896, "count": 18192, "self": 0.3853000780172806, "children": { "env_step": { "total": 337.6485526679903, "count": 18192, "self": 264.4315416549789, "children": { "SubprocessEnvManager._take_step": { "total": 72.99667990601688, "count": 18192, "self": 1.2824491910241704, "children": { "TorchPolicy.evaluate": { "total": 71.71423071499271, "count": 18192, "self": 71.71423071499271 } } }, "workers": { "total": 0.22033110699453573, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 462.2582104230082, "count": 18192, "is_parallel": true, "self": 229.99585524902363, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004842494999820701, "count": 1, "is_parallel": true, "self": 0.003291819999958534, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015506749998621672, "count": 10, "is_parallel": true, "self": 0.0015506749998621672 } } }, "UnityEnvironment.step": { "total": 0.03848596800003179, "count": 1, "is_parallel": true, "self": 0.0006792870001390838, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004384899998512992, "count": 1, "is_parallel": true, "self": 0.0004384899998512992 }, "communicator.exchange": { "total": 0.03534130899993215, "count": 1, "is_parallel": true, "self": 0.03534130899993215 }, "steps_from_proto": { "total": 0.0020268820001092536, "count": 1, "is_parallel": true, "self": 0.0003847879997920245, "children": { "_process_rank_one_or_two_observation": { "total": 0.001642094000317229, "count": 10, "is_parallel": true, "self": 0.001642094000317229 } } } } } } }, "UnityEnvironment.step": { "total": 232.2623551739846, "count": 18191, "is_parallel": true, "self": 10.674307969003166, "children": { "UnityEnvironment._generate_step_input": { "total": 5.60140051599069, "count": 18191, "is_parallel": true, "self": 5.60140051599069 }, "communicator.exchange": { "total": 177.57984047298123, "count": 18191, "is_parallel": true, "self": 177.57984047298123 }, "steps_from_proto": { "total": 38.4068062160095, "count": 18191, "is_parallel": true, "self": 6.791489322977441, "children": { "_process_rank_one_or_two_observation": { "total": 31.61531689303206, "count": 181910, "is_parallel": true, "self": 31.61531689303206 } } } } } } } } } } }, "trainer_advance": { "total": 122.56261266598199, "count": 18192, "self": 0.4408097229706982, "children": { "process_trajectory": { "total": 27.867867813010207, "count": 18192, "self": 27.42719875101011, "children": { "RLTrainer._checkpoint": { "total": 0.44066906200009726, "count": 4, "self": 0.44066906200009726 } } }, "_update_policy": { "total": 94.25393513000108, "count": 90, "self": 38.41301379899869, "children": { "TorchPPOOptimizer.update": { "total": 55.84092133100239, "count": 4587, "self": 55.84092133100239 } } } } } } }, "trainer_threads": { "total": 1.0139999631064711e-06, "count": 1, "self": 1.0139999631064711e-06 }, "TrainerController._save_models": { "total": 0.12018277800007127, "count": 1, "self": 0.0009114899999076442, "children": { "RLTrainer._checkpoint": { "total": 0.11927128800016362, "count": 1, "self": 0.11927128800016362 } } } } } } }