{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9024656414985657, "min": 0.9024656414985657, "max": 2.863783121109009, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8616.7421875, "min": 8616.7421875, "max": 29328.00390625, "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": 13.102996826171875, "min": 0.4203854203224182, "max": 13.144856452941895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2555.08447265625, "min": 81.55477142333984, "max": 2681.55078125, "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": 0.07108683886027019, "min": 0.06018570321383794, "max": 0.07475182900008948, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28434735544108075, "min": 0.24074281285535176, "max": 0.3737591450004474, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18356770981906675, "min": 0.11174615296790852, "max": 0.2890019120538936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.734270839276267, "min": 0.4469846118716341, "max": 1.445009560269468, "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": 25.75, "min": 3.409090909090909, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 150.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.409090909090909, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 150.0, "max": 1428.0, "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": "1791707722", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mla/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --torch-device=cpu --force", "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": "1791708188" }, "total": 465.371230576, "count": 1, "self": 0.4757137729993701, "children": { "run_training.setup": { "total": 0.019788991000496026, "count": 1, "self": 0.019788991000496026 }, "TrainerController.start_learning": { "total": 464.87572781200015, "count": 1, "self": 0.6212293339676762, "children": { "TrainerController._reset_env": { "total": 1.6551914449992182, "count": 1, "self": 1.6551914449992182 }, "TrainerController.advance": { "total": 462.5412020670328, "count": 18202, "self": 0.2610915709492474, "children": { "env_step": { "total": 462.2801104960836, "count": 18202, "self": 358.56529017218327, "children": { "SubprocessEnvManager._take_step": { "total": 103.43561240690906, "count": 18202, "self": 1.4567083049560097, "children": { "TorchPolicy.evaluate": { "total": 101.97890410195305, "count": 18202, "self": 101.97890410195305 } } }, "workers": { "total": 0.279207916991254, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 462.9023879178794, "count": 18202, "is_parallel": true, "self": 200.94830132193874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002097094999953697, "count": 1, "is_parallel": true, "self": 0.0006352860000333749, "children": { "_process_rank_one_or_two_observation": { "total": 0.001461808999920322, "count": 10, "is_parallel": true, "self": 0.001461808999920322 } } }, "UnityEnvironment.step": { "total": 0.10346287799984566, "count": 1, "is_parallel": true, "self": 0.0005454589991131797, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003393770002730889, "count": 1, "is_parallel": true, "self": 0.0003393770002730889 }, "communicator.exchange": { "total": 0.09846601900062524, "count": 1, "is_parallel": true, "self": 0.09846601900062524 }, "steps_from_proto": { "total": 0.004112022999834153, "count": 1, "is_parallel": true, "self": 0.00038172399945324287, "children": { "_process_rank_one_or_two_observation": { "total": 0.00373029900038091, "count": 10, "is_parallel": true, "self": 0.00373029900038091 } } } } } } }, "UnityEnvironment.step": { "total": 261.9540865959407, "count": 18201, "is_parallel": true, "self": 11.380690279870578, "children": { "UnityEnvironment._generate_step_input": { "total": 5.768782094028211, "count": 18201, "is_parallel": true, "self": 5.768782094028211 }, "communicator.exchange": { "total": 202.79572317398834, "count": 18201, "is_parallel": true, "self": 202.79572317398834 }, "steps_from_proto": { "total": 42.008891048053556, "count": 18201, "is_parallel": true, "self": 8.152361515111807, "children": { "_process_rank_one_or_two_observation": { "total": 33.85652953294175, "count": 182010, "is_parallel": true, "self": 33.85652953294175 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014148700029181782, "count": 1, "self": 0.00014148700029181782, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 459.12596655047673, "count": 417149, "is_parallel": true, "self": 9.614723687939659, "children": { "process_trajectory": { "total": 246.77722071053267, "count": 417149, "is_parallel": true, "self": 246.01205263453448, "children": { "RLTrainer._checkpoint": { "total": 0.76516807599819, "count": 4, "is_parallel": true, "self": 0.76516807599819 } } }, "_update_policy": { "total": 202.7340221520044, "count": 90, "is_parallel": true, "self": 48.303354275002675, "children": { "TorchPPOOptimizer.update": { "total": 154.43066787700172, "count": 4587, "is_parallel": true, "self": 154.43066787700172 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05796347900013643, "count": 1, "self": 0.0007548040002802736, "children": { "RLTrainer._checkpoint": { "total": 0.05720867499985616, "count": 1, "self": 0.05720867499985616 } } } } } } }