{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0591418743133545, "min": 1.0591418743133545, "max": 2.864712715148926, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10205.890625, "min": 10205.890625, "max": 29337.5234375, "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": 12.073869705200195, "min": 0.3839539587497711, "max": 12.073869705200195, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2354.404541015625, "min": 74.48706817626953, "max": 2426.869873046875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06646537197786316, "min": 0.061501281660086685, "max": 0.07729435361500955, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26586148791145264, "min": 0.26364241908167435, "max": 0.36283532822990844, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20401351449682434, "min": 0.13215004675222708, "max": 0.2682116824183978, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8160540579872974, "min": 0.5286001870089083, "max": 1.3369165208994174, "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": 24.15909090909091, "min": 3.4318181818181817, "max": 24.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1063.0, "min": 151.0, "max": 1325.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.15909090909091, "min": 3.4318181818181817, "max": 24.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1063.0, "min": 151.0, "max": 1325.0, "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": "1703515103", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703515577" }, "total": 473.791866251, "count": 1, "self": 0.6339675919998626, "children": { "run_training.setup": { "total": 0.05127992200004883, "count": 1, "self": 0.05127992200004883 }, "TrainerController.start_learning": { "total": 473.1066187370001, "count": 1, "self": 0.6244801569957872, "children": { "TrainerController._reset_env": { "total": 3.467802487999961, "count": 1, "self": 3.467802487999961 }, "TrainerController.advance": { "total": 468.87878358200453, "count": 18215, "self": 0.29205099800742573, "children": { "env_step": { "total": 468.5867325839971, "count": 18215, "self": 309.4357022999808, "children": { "SubprocessEnvManager._take_step": { "total": 158.85094266099475, "count": 18215, "self": 1.558314215999303, "children": { "TorchPolicy.evaluate": { "total": 157.29262844499544, "count": 18215, "self": 157.29262844499544 } } }, "workers": { "total": 0.3000876230215681, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 471.67992350799045, "count": 18215, "is_parallel": true, "self": 232.39732348799532, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005212222000068323, "count": 1, "is_parallel": true, "self": 0.0031697779999149134, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020424440001534094, "count": 10, "is_parallel": true, "self": 0.0020424440001534094 } } }, "UnityEnvironment.step": { "total": 0.046039331999963906, "count": 1, "is_parallel": true, "self": 0.0006478619999370494, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044607799998175324, "count": 1, "is_parallel": true, "self": 0.00044607799998175324 }, "communicator.exchange": { "total": 0.04278746099998898, "count": 1, "is_parallel": true, "self": 0.04278746099998898 }, "steps_from_proto": { "total": 0.0021579310000561236, "count": 1, "is_parallel": true, "self": 0.00042819499992674537, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017297360001293782, "count": 10, "is_parallel": true, "self": 0.0017297360001293782 } } } } } } }, "UnityEnvironment.step": { "total": 239.28260001999513, "count": 18214, "is_parallel": true, "self": 11.016970321012423, "children": { "UnityEnvironment._generate_step_input": { "total": 5.684162869991724, "count": 18214, "is_parallel": true, "self": 5.684162869991724 }, "communicator.exchange": { "total": 186.65125855799283, "count": 18214, "is_parallel": true, "self": 186.65125855799283 }, "steps_from_proto": { "total": 35.93020827099815, "count": 18214, "is_parallel": true, "self": 6.679311237018624, "children": { "_process_rank_one_or_two_observation": { "total": 29.250897033979527, "count": 182140, "is_parallel": true, "self": 29.250897033979527 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012070899992977502, "count": 1, "self": 0.00012070899992977502, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.21933048406277, "count": 679195, "is_parallel": true, "self": 14.380588106021378, "children": { "process_trajectory": { "total": 255.5627697700421, "count": 679195, "is_parallel": true, "self": 254.83835440904204, "children": { "RLTrainer._checkpoint": { "total": 0.7244153610000694, "count": 4, "is_parallel": true, "self": 0.7244153610000694 } } }, "_update_policy": { "total": 193.27597260799928, "count": 90, "is_parallel": true, "self": 60.68561321700372, "children": { "TorchPPOOptimizer.update": { "total": 132.59035939099556, "count": 4584, "is_parallel": true, "self": 132.59035939099556 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13543180099986785, "count": 1, "self": 0.0012936010000430542, "children": { "RLTrainer._checkpoint": { "total": 0.1341381999998248, "count": 1, "self": 0.1341381999998248 } } } } } } }