{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8289297819137573, "min": 0.8042367696762085, "max": 2.8574557304382324, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8242.8779296875, "min": 8006.17724609375, "max": 29200.33984375, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9984.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9984.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.28245735168457, "min": 0.3585469424724579, "max": 13.314485549926758, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 4701.98974609375, "min": 123.69869995117188, "max": 4710.0068359375, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07566246719318716, "min": 0.058162399131248876, "max": 0.07566246719318716, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3783123359659358, "min": 0.2326495965249955, "max": 0.3783123359659358, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17524200146104776, "min": 0.09616112322135664, "max": 0.27400995790958405, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8762100073052388, "min": 0.38464449288542657, "max": 1.3700497895479202, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000028e-06, "min": 3.0528989824000028e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5264494912000015e-05, "min": 1.5264494912000015e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.036363636363635, "min": 2.8863636363636362, "max": 26.636363636363637, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1432.0, "min": 127.0, "max": 1432.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.036363636363635, "min": 2.8863636363636362, "max": 26.636363636363637, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1432.0, "min": 127.0, "max": 1432.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704379471", "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": "1704380727" }, "total": 1256.0156243299998, "count": 1, "self": 0.4394985349997569, "children": { "run_training.setup": { "total": 0.06132176899996011, "count": 1, "self": 0.06132176899996011 }, "TrainerController.start_learning": { "total": 1255.514804026, "count": 1, "self": 1.6249335229742883, "children": { "TrainerController._reset_env": { "total": 3.5388134150000496, "count": 1, "self": 3.5388134150000496 }, "TrainerController.advance": { "total": 1250.2773375190254, "count": 45469, "self": 0.7951087540209301, "children": { "env_step": { "total": 1249.4822287650045, "count": 45469, "self": 874.6768752569053, "children": { "SubprocessEnvManager._take_step": { "total": 373.96118103304957, "count": 45469, "self": 4.3938079401202685, "children": { "TorchPolicy.evaluate": { "total": 369.5673730929293, "count": 45469, "self": 369.5673730929293 } } }, "workers": { "total": 0.8441724750496178, "count": 45469, "self": 0.0, "children": { "worker_root": { "total": 1251.9529425429964, "count": 45469, "is_parallel": true, "self": 625.8283418069882, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004499985000165907, "count": 1, "is_parallel": true, "self": 0.003100859000142009, "children": { "_process_rank_one_or_two_observation": { "total": 0.001399126000023898, "count": 10, "is_parallel": true, "self": 0.001399126000023898 } } }, "UnityEnvironment.step": { "total": 0.06489778600007412, "count": 1, "is_parallel": true, "self": 0.0007372700001724297, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043066099988209317, "count": 1, "is_parallel": true, "self": 0.00043066099988209317 }, "communicator.exchange": { "total": 0.0616690980000385, "count": 1, "is_parallel": true, "self": 0.0616690980000385 }, "steps_from_proto": { "total": 0.002060756999981095, "count": 1, "is_parallel": true, "self": 0.00040886200008571905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016518949998953758, "count": 10, "is_parallel": true, "self": 0.0016518949998953758 } } } } } } }, "UnityEnvironment.step": { "total": 626.1246007360082, "count": 45468, "is_parallel": true, "self": 30.627199557998438, "children": { "UnityEnvironment._generate_step_input": { "total": 15.023184105016071, "count": 45468, "is_parallel": true, "self": 15.023184105016071 }, "communicator.exchange": { "total": 488.97764874300447, "count": 45468, "is_parallel": true, "self": 488.97764874300447 }, "steps_from_proto": { "total": 91.49656832998926, "count": 45468, "is_parallel": true, "self": 17.56770795895818, "children": { "_process_rank_one_or_two_observation": { "total": 73.92886037103108, "count": 454680, "is_parallel": true, "self": 73.92886037103108 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016340199999831384, "count": 1, "self": 0.00016340199999831384, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1232.063051319615, "count": 2168053, "is_parallel": true, "self": 45.85620751467741, "children": { "process_trajectory": { "total": 809.2252007309387, "count": 2168053, "is_parallel": true, "self": 807.6724849419377, "children": { "RLTrainer._checkpoint": { "total": 1.552715789001013, "count": 10, "is_parallel": true, "self": 1.552715789001013 } } }, "_update_policy": { "total": 376.98164307399884, "count": 227, "is_parallel": true, "self": 136.8501465150032, "children": { "TorchPPOOptimizer.update": { "total": 240.13149655899565, "count": 11574, "is_parallel": true, "self": 240.13149655899565 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07355616700033352, "count": 1, "self": 0.0007833460003894288, "children": { "RLTrainer._checkpoint": { "total": 0.07277282099994409, "count": 1, "self": 0.07277282099994409 } } } } } } }