{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9195731282234192, "min": 0.9195731282234192, "max": 2.860503911972046, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8739.623046875, "min": 8739.623046875, "max": 29200.0234375, "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": 12.956710815429688, "min": 0.43210095167160034, "max": 12.956710815429688, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.55859375, "min": 83.82758331298828, "max": 2600.103271484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06572493303432494, "min": 0.06157199210771497, "max": 0.07597254983031912, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2628997321372998, "min": 0.24628796843085987, "max": 0.3798627491515956, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19169934302130165, "min": 0.12755530311123414, "max": 0.26826779632007375, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7667973720852066, "min": 0.5102212124449366, "max": 1.3228805354412865, "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.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.Environment.CumulativeReward.mean": { "value": 26.318181818181817, "min": 3.5454545454545454, "max": 26.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1158.0, "min": 156.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.318181818181817, "min": 3.5454545454545454, "max": 26.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1158.0, "min": 156.0, "max": 1374.0, "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": "1746429678", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746430096" }, "total": 417.52091276399995, "count": 1, "self": 0.4366074120000576, "children": { "run_training.setup": { "total": 0.024022534999971867, "count": 1, "self": 0.024022534999971867 }, "TrainerController.start_learning": { "total": 417.0602828169999, "count": 1, "self": 0.34947017199056063, "children": { "TrainerController._reset_env": { "total": 3.361570465999989, "count": 1, "self": 3.361570465999989 }, "TrainerController.advance": { "total": 413.2711230430094, "count": 18192, "self": 0.366244513007814, "children": { "env_step": { "total": 291.6353718710019, "count": 18192, "self": 223.56661439299637, "children": { "SubprocessEnvManager._take_step": { "total": 67.87174953900706, "count": 18192, "self": 1.1964033660201494, "children": { "TorchPolicy.evaluate": { "total": 66.6753461729869, "count": 18192, "self": 66.6753461729869 } } }, "workers": { "total": 0.19700793899846758, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 415.7317490890025, "count": 18192, "is_parallel": true, "self": 219.30966908499397, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005887740000048325, "count": 1, "is_parallel": true, "self": 0.0035937109998940286, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022940290001542962, "count": 10, "is_parallel": true, "self": 0.0022940290001542962 } } }, "UnityEnvironment.step": { "total": 0.036716190999982246, "count": 1, "is_parallel": true, "self": 0.0005995279999524428, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042741300001125637, "count": 1, "is_parallel": true, "self": 0.00042741300001125637 }, "communicator.exchange": { "total": 0.033912352000015744, "count": 1, "is_parallel": true, "self": 0.033912352000015744 }, "steps_from_proto": { "total": 0.0017768980000028023, "count": 1, "is_parallel": true, "self": 0.0003548069998942083, "children": { "_process_rank_one_or_two_observation": { "total": 0.001422091000108594, "count": 10, "is_parallel": true, "self": 0.001422091000108594 } } } } } } }, "UnityEnvironment.step": { "total": 196.42208000400854, "count": 18191, "is_parallel": true, "self": 9.694660798005657, "children": { "UnityEnvironment._generate_step_input": { "total": 5.419850305001205, "count": 18191, "is_parallel": true, "self": 5.419850305001205 }, "communicator.exchange": { "total": 151.08826464499452, "count": 18191, "is_parallel": true, "self": 151.08826464499452 }, "steps_from_proto": { "total": 30.21930425600715, "count": 18191, "is_parallel": true, "self": 5.451400658046623, "children": { "_process_rank_one_or_two_observation": { "total": 24.767903597960526, "count": 181910, "is_parallel": true, "self": 24.767903597960526 } } } } } } } } } } }, "trainer_advance": { "total": 121.26950665899972, "count": 18192, "self": 0.4353745430039453, "children": { "process_trajectory": { "total": 26.287599333996013, "count": 18192, "self": 25.830725902996164, "children": { "RLTrainer._checkpoint": { "total": 0.456873430999849, "count": 4, "self": 0.456873430999849 } } }, "_update_policy": { "total": 94.54653278199976, "count": 90, "self": 38.8855485899993, "children": { "TorchPPOOptimizer.update": { "total": 55.660984192000456, "count": 4587, "self": 55.660984192000456 } } } } } } }, "trainer_threads": { "total": 9.590000900061568e-07, "count": 1, "self": 9.590000900061568e-07 }, "TrainerController._save_models": { "total": 0.07811817699985113, "count": 1, "self": 0.0008401529996717727, "children": { "RLTrainer._checkpoint": { "total": 0.07727802400017936, "count": 1, "self": 0.07727802400017936 } } } } } } }