{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9706457257270813, "min": 0.9706457257270813, "max": 2.860203981399536, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9299.7568359375, "min": 9299.7568359375, "max": 29291.349609375, "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": 12.640176773071289, "min": 0.31891679763793945, "max": 12.640176773071289, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2464.83447265625, "min": 61.8698616027832, "max": 2548.16943359375, "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": 0.06754651650315317, "min": 0.061233779301426906, "max": 0.07507436258382251, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2701860660126127, "min": 0.24493511720570763, "max": 0.36727603578793944, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17306161065604173, "min": 0.0932834271071068, "max": 0.265717024969704, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6922464426241669, "min": 0.3731337084284272, "max": 1.3156634154273017, "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": 25.0, "min": 2.477272727272727, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 109.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 2.477272727272727, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 109.0, "max": 1381.0, "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": "1704887506", "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": "1704887978" }, "total": 471.7304414299999, "count": 1, "self": 0.7426354510000124, "children": { "run_training.setup": { "total": 0.05433491899998444, "count": 1, "self": 0.05433491899998444 }, "TrainerController.start_learning": { "total": 470.93347105999993, "count": 1, "self": 0.6066381250012682, "children": { "TrainerController._reset_env": { "total": 3.1401477849999537, "count": 1, "self": 3.1401477849999537 }, "TrainerController.advance": { "total": 467.0530700659987, "count": 18208, "self": 0.3027814530046271, "children": { "env_step": { "total": 466.7502886129941, "count": 18208, "self": 307.29351370600034, "children": { "SubprocessEnvManager._take_step": { "total": 159.15822561899267, "count": 18208, "self": 1.660958584994205, "children": { "TorchPolicy.evaluate": { "total": 157.49726703399847, "count": 18208, "self": 157.49726703399847 } } }, "workers": { "total": 0.2985492880010838, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 469.5212561560063, "count": 18208, "is_parallel": true, "self": 232.29642956701014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005193681999969613, "count": 1, "is_parallel": true, "self": 0.0038628960000437473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013307859999258653, "count": 10, "is_parallel": true, "self": 0.0013307859999258653 } } }, "UnityEnvironment.step": { "total": 0.03991887800003724, "count": 1, "is_parallel": true, "self": 0.0007089170001108869, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045139499997048915, "count": 1, "is_parallel": true, "self": 0.00045139499997048915 }, "communicator.exchange": { "total": 0.036643749000006665, "count": 1, "is_parallel": true, "self": 0.036643749000006665 }, "steps_from_proto": { "total": 0.0021148169999491984, "count": 1, "is_parallel": true, "self": 0.0004214979999233037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016933190000258946, "count": 10, "is_parallel": true, "self": 0.0016933190000258946 } } } } } } }, "UnityEnvironment.step": { "total": 237.22482658899617, "count": 18207, "is_parallel": true, "self": 11.018511320997277, "children": { "UnityEnvironment._generate_step_input": { "total": 5.741130186999612, "count": 18207, "is_parallel": true, "self": 5.741130186999612 }, "communicator.exchange": { "total": 184.5242414839954, "count": 18207, "is_parallel": true, "self": 184.5242414839954 }, "steps_from_proto": { "total": 35.940943597003866, "count": 18207, "is_parallel": true, "self": 6.711796213993239, "children": { "_process_rank_one_or_two_observation": { "total": 29.229147383010627, "count": 182070, "is_parallel": true, "self": 29.229147383010627 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015532199995504925, "count": 1, "self": 0.00015532199995504925, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.0736380989036, "count": 692287, "is_parallel": true, "self": 15.010286051863147, "children": { "process_trajectory": { "total": 255.53219531104014, "count": 692287, "is_parallel": true, "self": 254.8354502110401, "children": { "RLTrainer._checkpoint": { "total": 0.6967451000000437, "count": 4, "is_parallel": true, "self": 0.6967451000000437 } } }, "_update_policy": { "total": 190.5311567360003, "count": 90, "is_parallel": true, "self": 60.15655153999694, "children": { "TorchPPOOptimizer.update": { "total": 130.37460519600336, "count": 4587, "is_parallel": true, "self": 130.37460519600336 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1334597620000295, "count": 1, "self": 0.0012187280000262035, "children": { "RLTrainer._checkpoint": { "total": 0.1322410340000033, "count": 1, "self": 0.1322410340000033 } } } } } } }