{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8007888197898865, "min": 0.8007888197898865, "max": 2.856308698654175, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7645.931640625, "min": 7645.931640625, "max": 29251.45703125, "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": 12.747394561767578, "min": 0.504061222076416, "max": 12.747394561767578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2485.741943359375, "min": 97.78787231445312, "max": 2607.41064453125, "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": 0.06746468520025548, "min": 0.061063023320029435, "max": 0.07288446154459106, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2698587408010219, "min": 0.24425209328011774, "max": 0.3612456432721742, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2074793352215898, "min": 0.14158183585067152, "max": 0.2731542793266914, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8299173408863592, "min": 0.5663273434026861, "max": 1.3175316070224725, "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": 25.15909090909091, "min": 3.590909090909091, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 158.0, "max": 1371.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.590909090909091, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 158.0, "max": 1371.0, "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": "1709923585", "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": "1709924042" }, "total": 456.64192998500005, "count": 1, "self": 0.3917750440000418, "children": { "run_training.setup": { "total": 0.05496624200009137, "count": 1, "self": 0.05496624200009137 }, "TrainerController.start_learning": { "total": 456.1951886989999, "count": 1, "self": 0.5932693410057936, "children": { "TrainerController._reset_env": { "total": 3.0240062730000545, "count": 1, "self": 3.0240062730000545 }, "TrainerController.advance": { "total": 452.48523862999434, "count": 18199, "self": 0.2753704389942868, "children": { "env_step": { "total": 452.20986819100006, "count": 18199, "self": 293.5578314489994, "children": { "SubprocessEnvManager._take_step": { "total": 158.36035528600132, "count": 18199, "self": 1.5059221530021887, "children": { "TorchPolicy.evaluate": { "total": 156.85443313299913, "count": 18199, "self": 156.85443313299913 } } }, "workers": { "total": 0.29168145599930995, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 455.0510900660057, "count": 18199, "is_parallel": true, "self": 226.1296118520097, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006274204000078498, "count": 1, "is_parallel": true, "self": 0.004673914000022705, "children": { "_process_rank_one_or_two_observation": { "total": 0.001600290000055793, "count": 10, "is_parallel": true, "self": 0.001600290000055793 } } }, "UnityEnvironment.step": { "total": 0.03710159100000965, "count": 1, "is_parallel": true, "self": 0.0007041969998908826, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004051570000456195, "count": 1, "is_parallel": true, "self": 0.0004051570000456195 }, "communicator.exchange": { "total": 0.03391716999999517, "count": 1, "is_parallel": true, "self": 0.03391716999999517 }, "steps_from_proto": { "total": 0.002075067000077979, "count": 1, "is_parallel": true, "self": 0.0003912650000756912, "children": { "_process_rank_one_or_two_observation": { "total": 0.001683802000002288, "count": 10, "is_parallel": true, "self": 0.001683802000002288 } } } } } } }, "UnityEnvironment.step": { "total": 228.921478213996, "count": 18198, "is_parallel": true, "self": 10.452741054000057, "children": { "UnityEnvironment._generate_step_input": { "total": 5.438771415989322, "count": 18198, "is_parallel": true, "self": 5.438771415989322 }, "communicator.exchange": { "total": 178.4317559669928, "count": 18198, "is_parallel": true, "self": 178.4317559669928 }, "steps_from_proto": { "total": 34.598209777013835, "count": 18198, "is_parallel": true, "self": 6.522124585003212, "children": { "_process_rank_one_or_two_observation": { "total": 28.076085192010623, "count": 181980, "is_parallel": true, "self": 28.076085192010623 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019776899989665253, "count": 1, "self": 0.00019776899989665253, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 446.7300227969679, "count": 689555, "is_parallel": true, "self": 15.069589274048326, "children": { "process_trajectory": { "total": 247.6464772649199, "count": 689555, "is_parallel": true, "self": 246.88421632991992, "children": { "RLTrainer._checkpoint": { "total": 0.762260934999972, "count": 4, "is_parallel": true, "self": 0.762260934999972 } } }, "_update_policy": { "total": 184.01395625799967, "count": 90, "is_parallel": true, "self": 51.507661463000886, "children": { "TorchPPOOptimizer.update": { "total": 132.50629479499878, "count": 4587, "is_parallel": true, "self": 132.50629479499878 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09247668599982717, "count": 1, "self": 0.0009596619997864764, "children": { "RLTrainer._checkpoint": { "total": 0.09151702400004069, "count": 1, "self": 0.09151702400004069 } } } } } } }