{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.803484320640564, "min": 0.7628971338272095, "max": 2.8903205394744873, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 565.6529541015625, "min": 537.07958984375, "max": 4298.21630859375, "count": 200 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 960.0, "max": 199984.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 960.0, "max": 199984.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.181304931640625, "min": 0.06443431973457336, "max": 13.206515312194824, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 210.90087890625, "min": 0.9665148258209229, "max": 342.58013916015625, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07686452096437707, "min": 0.0507554501533627, "max": 0.09012304773262027, "count": 90 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.07686452096437707, "min": 0.0507554501533627, "max": 0.09012304773262027, "count": 90 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20188107180829143, "min": 0.10993161987440259, "max": 0.3576154013474782, "count": 90 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.20188107180829143, "min": 0.10993161987440259, "max": 0.3576154013474782, "count": 90 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.1320989560000013e-06, "min": 3.1320989560000013e-06, "max": 0.000296832001056, "count": 90 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.1320989560000013e-06, "min": 3.1320989560000013e-06, "max": 0.000296832001056, "count": 90 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101044, "min": 0.101044, "max": 0.198944, "count": 90 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.101044, "min": 0.101044, "max": 0.198944, "count": 90 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.209560000000005e-05, "min": 6.209560000000005e-05, "max": 0.0049473056, "count": 90 }, "SnowballTarget.Policy.Beta.sum": { "value": 6.209560000000005e-05, "min": 6.209560000000005e-05, "max": 0.0049473056, "count": 90 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 90 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 90 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 29.0, "min": 3.0, "max": 30.0, "count": 108 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 29.0, "min": 3.0, "max": 296.0, "count": 108 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 29.0, "min": 3.0, "max": 30.0, "count": 108 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 29.0, "min": 3.0, "max": 296.0, "count": 108 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736831740", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736832172" }, "total": 431.8959257030001, "count": 1, "self": 0.42808311700082413, "children": { "run_training.setup": { "total": 0.05584461599983115, "count": 1, "self": 0.05584461599983115 }, "TrainerController.start_learning": { "total": 431.41199796999945, "count": 1, "self": 0.3641833590127135, "children": { "TrainerController._reset_env": { "total": 1.941880212000342, "count": 1, "self": 1.941880212000342 }, "TrainerController.advance": { "total": 429.01779893198636, "count": 18192, "self": 0.37645742895165313, "children": { "env_step": { "total": 301.3302726129846, "count": 18192, "self": 230.04266327501045, "children": { "SubprocessEnvManager._take_step": { "total": 71.06606058199532, "count": 18192, "self": 1.2500780270042924, "children": { "TorchPolicy.evaluate": { "total": 69.81598255499102, "count": 18192, "self": 69.81598255499102 } } }, "workers": { "total": 0.22154875597880164, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 429.78371514798255, "count": 18192, "is_parallel": true, "self": 228.42536628699145, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002265427000111231, "count": 1, "is_parallel": true, "self": 0.000676131000091118, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015892960000201128, "count": 10, "is_parallel": true, "self": 0.0015892960000201128 } } }, "UnityEnvironment.step": { "total": 0.03557796499990218, "count": 1, "is_parallel": true, "self": 0.0008088620002126845, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039372099990941933, "count": 1, "is_parallel": true, "self": 0.00039372099990941933 }, "communicator.exchange": { "total": 0.03227820199981579, "count": 1, "is_parallel": true, "self": 0.03227820199981579 }, "steps_from_proto": { "total": 0.0020971799999642826, "count": 1, "is_parallel": true, "self": 0.00042500300014580716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016721769998184755, "count": 10, "is_parallel": true, "self": 0.0016721769998184755 } } } } } } }, "UnityEnvironment.step": { "total": 201.3583488609911, "count": 18191, "is_parallel": true, "self": 9.91710704694924, "children": { "UnityEnvironment._generate_step_input": { "total": 5.416393375051484, "count": 18191, "is_parallel": true, "self": 5.416393375051484 }, "communicator.exchange": { "total": 153.93211714395966, "count": 18191, "is_parallel": true, "self": 153.93211714395966 }, "steps_from_proto": { "total": 32.09273129503072, "count": 18191, "is_parallel": true, "self": 5.807635553239379, "children": { "_process_rank_one_or_two_observation": { "total": 26.285095741791338, "count": 181910, "is_parallel": true, "self": 26.285095741791338 } } } } } } } } } } }, "trainer_advance": { "total": 127.31106889005014, "count": 18192, "self": 0.4472302320777999, "children": { "process_trajectory": { "total": 29.12317135297417, "count": 18192, "self": 28.60563932797413, "children": { "RLTrainer._checkpoint": { "total": 0.5175320250000368, "count": 4, "self": 0.5175320250000368 } } }, "_update_policy": { "total": 97.74066730499817, "count": 90, "self": 40.48459548499795, "children": { "TorchPPOOptimizer.update": { "total": 57.256071820000216, "count": 4587, "self": 57.256071820000216 } } } } } } }, "trainer_threads": { "total": 1.0730000212788582e-06, "count": 1, "self": 1.0730000212788582e-06 }, "TrainerController._save_models": { "total": 0.08813439400000789, "count": 1, "self": 0.0011575770004128572, "children": { "RLTrainer._checkpoint": { "total": 0.08697681699959503, "count": 1, "self": 0.08697681699959503 } } } } } } }