{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2145763635635376, "min": 1.2145763635635376, "max": 2.880887985229492, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11636.8564453125, "min": 11636.8564453125, "max": 29629.93359375, "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": 11.869561195373535, "min": 0.518143355846405, "max": 11.869561195373535, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2314.564453125, "min": 100.51980590820312, "max": 2393.40576171875, "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": 0.06853132754422761, "min": 0.06319104195669448, "max": 0.07807384714023119, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27412531017691044, "min": 0.2527641678267779, "max": 0.39036923570115595, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2884418976803621, "min": 0.11914607437382288, "max": 0.3104281196407243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1537675907214484, "min": 0.4765842974952915, "max": 1.5521405982036216, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6940973060000025e-06, "min": 2.6940973060000025e-06, "max": 9.729400270599998e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.077638922400001e-05, "min": 1.077638922400001e-05, "max": 0.0004617200382800001, "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": 23.227272727272727, "min": 3.1136363636363638, "max": 23.654545454545456, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1022.0, "min": 137.0, "max": 1301.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.227272727272727, "min": 3.1136363636363638, "max": 23.654545454545456, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1022.0, "min": 137.0, "max": 1301.0, "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": "1688541799", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688542268" }, "total": 469.69434691600003, "count": 1, "self": 0.7981569219999756, "children": { "run_training.setup": { "total": 0.044382170999995196, "count": 1, "self": 0.044382170999995196 }, "TrainerController.start_learning": { "total": 468.85180782300006, "count": 1, "self": 0.537732630008577, "children": { "TrainerController._reset_env": { "total": 4.13971926100001, "count": 1, "self": 4.13971926100001 }, "TrainerController.advance": { "total": 463.8475242779915, "count": 18224, "self": 0.2560670499885873, "children": { "env_step": { "total": 463.5914572280029, "count": 18224, "self": 327.2103085420039, "children": { "SubprocessEnvManager._take_step": { "total": 136.12111988300188, "count": 18224, "self": 1.780967142002197, "children": { "TorchPolicy.evaluate": { "total": 134.34015274099968, "count": 18224, "self": 134.34015274099968 } } }, "workers": { "total": 0.26002880299714093, "count": 18224, "self": 0.0, "children": { "worker_root": { "total": 467.2377561890001, "count": 18224, "is_parallel": true, "self": 230.41540283600233, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005513919999998507, "count": 1, "is_parallel": true, "self": 0.004011708999996699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015022110000018074, "count": 10, "is_parallel": true, "self": 0.0015022110000018074 } } }, "UnityEnvironment.step": { "total": 0.03747341999999776, "count": 1, "is_parallel": true, "self": 0.0006324400000323749, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003938719999894147, "count": 1, "is_parallel": true, "self": 0.0003938719999894147 }, "communicator.exchange": { "total": 0.03437955399999737, "count": 1, "is_parallel": true, "self": 0.03437955399999737 }, "steps_from_proto": { "total": 0.0020675539999785997, "count": 1, "is_parallel": true, "self": 0.0003784010000345006, "children": { "_process_rank_one_or_two_observation": { "total": 0.001689152999944099, "count": 10, "is_parallel": true, "self": 0.001689152999944099 } } } } } } }, "UnityEnvironment.step": { "total": 236.82235335299777, "count": 18223, "is_parallel": true, "self": 10.194885337985397, "children": { "UnityEnvironment._generate_step_input": { "total": 5.071841826005198, "count": 18223, "is_parallel": true, "self": 5.071841826005198 }, "communicator.exchange": { "total": 187.36831595900557, "count": 18223, "is_parallel": true, "self": 187.36831595900557 }, "steps_from_proto": { "total": 34.1873102300016, "count": 18223, "is_parallel": true, "self": 6.078637655002069, "children": { "_process_rank_one_or_two_observation": { "total": 28.10867257499953, "count": 182230, "is_parallel": true, "self": 28.10867257499953 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014781599998059392, "count": 1, "self": 0.00014781599998059392, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.84496338098035, "count": 399227, "is_parallel": true, "self": 8.3784439139651, "children": { "process_trajectory": { "total": 261.2316168280153, "count": 399227, "is_parallel": true, "self": 259.0551005220152, "children": { "RLTrainer._checkpoint": { "total": 2.17651630600011, "count": 4, "is_parallel": true, "self": 2.17651630600011 } } }, "_update_policy": { "total": 191.23490263899993, "count": 90, "is_parallel": true, "self": 75.48182241900133, "children": { "TorchPPOOptimizer.update": { "total": 115.7530802199986, "count": 4584, "is_parallel": true, "self": 115.7530802199986 } } } } } } } } }, "TrainerController._save_models": { "total": 0.3266838380000081, "count": 1, "self": 0.0011441919999697348, "children": { "RLTrainer._checkpoint": { "total": 0.3255396460000384, "count": 1, "self": 0.3255396460000384 } } } } } } }