{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7424570322036743, "min": 0.7424570322036743, "max": 2.8728978633880615, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7260.4873046875, "min": 7238.59619140625, "max": 29421.34765625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.564081192016602, "min": 0.4222921133041382, "max": 13.86706829071045, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2780.63671875, "min": 81.92466735839844, "max": 2828.8818359375, "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": 0.06349361954969081, "min": 0.06096216019382244, "max": 0.07548993266605333, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.317468097748454, "min": 0.24384864077528975, "max": 0.37266896648547043, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17269703772138148, "min": 0.13384080690779157, "max": 0.2730473832172506, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8634851886069074, "min": 0.5353632276311663, "max": 1.3291282320723812, "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": 26.69090909090909, "min": 3.3181818181818183, "max": 27.272727272727273, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1468.0, "min": 146.0, "max": 1500.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.69090909090909, "min": 3.3181818181818183, "max": 27.272727272727273, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1468.0, "min": 146.0, "max": 1500.0, "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": "1689530628", "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": "1689531766" }, "total": 1137.830814101, "count": 1, "self": 0.43652898799996365, "children": { "run_training.setup": { "total": 0.04162648099998023, "count": 1, "self": 0.04162648099998023 }, "TrainerController.start_learning": { "total": 1137.352658632, "count": 1, "self": 1.197892571983175, "children": { "TrainerController._reset_env": { "total": 4.111410257999978, "count": 1, "self": 4.111410257999978 }, "TrainerController.advance": { "total": 1131.897229610017, "count": 45500, "self": 0.5923195870141171, "children": { "env_step": { "total": 1131.3049100230028, "count": 45500, "self": 825.0084598060165, "children": { "SubprocessEnvManager._take_step": { "total": 305.6755188320143, "count": 45500, "self": 4.384614046994898, "children": { "TorchPolicy.evaluate": { "total": 301.2909047850194, "count": 45500, "self": 301.2909047850194 } } }, "workers": { "total": 0.620931384971982, "count": 45500, "self": 0.0, "children": { "worker_root": { "total": 1133.8241881649878, "count": 45500, "is_parallel": true, "self": 532.3521887960088, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006812465000052725, "count": 1, "is_parallel": true, "self": 0.005123583000340659, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016888819997120663, "count": 10, "is_parallel": true, "self": 0.0016888819997120663 } } }, "UnityEnvironment.step": { "total": 0.04091799200000423, "count": 1, "is_parallel": true, "self": 0.0009967490000235557, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043535099996461213, "count": 1, "is_parallel": true, "self": 0.00043535099996461213 }, "communicator.exchange": { "total": 0.03742620899993199, "count": 1, "is_parallel": true, "self": 0.03742620899993199 }, "steps_from_proto": { "total": 0.0020596830000840782, "count": 1, "is_parallel": true, "self": 0.0003472610004564558, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017124219996276224, "count": 10, "is_parallel": true, "self": 0.0017124219996276224 } } } } } } }, "UnityEnvironment.step": { "total": 601.471999368979, "count": 45499, "is_parallel": true, "self": 26.473422094982084, "children": { "UnityEnvironment._generate_step_input": { "total": 12.94251987898042, "count": 45499, "is_parallel": true, "self": 12.94251987898042 }, "communicator.exchange": { "total": 475.1824613870084, "count": 45499, "is_parallel": true, "self": 475.1824613870084 }, "steps_from_proto": { "total": 86.87359600800812, "count": 45499, "is_parallel": true, "self": 15.480728640993448, "children": { "_process_rank_one_or_two_observation": { "total": 71.39286736701467, "count": 454990, "is_parallel": true, "self": 71.39286736701467 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.0205999994213926e-05, "count": 1, "self": 4.0205999994213926e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1123.2151634338734, "count": 1050186, "is_parallel": true, "self": 23.101019192988588, "children": { "process_trajectory": { "total": 610.8098345558825, "count": 1050186, "is_parallel": true, "self": 608.2720062568826, "children": { "RLTrainer._checkpoint": { "total": 2.537828298999898, "count": 10, "is_parallel": true, "self": 2.537828298999898 } } }, "_update_policy": { "total": 489.3043096850023, "count": 227, "is_parallel": true, "self": 192.8302572620039, "children": { "TorchPPOOptimizer.update": { "total": 296.4740524229984, "count": 11574, "is_parallel": true, "self": 296.4740524229984 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1460859859998891, "count": 1, "self": 0.0009184329996969609, "children": { "RLTrainer._checkpoint": { "total": 0.14516755300019213, "count": 1, "self": 0.14516755300019213 } } } } } } }