{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.43655845522880554, "min": 0.43655845522880554, "max": 0.661785900592804, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4187.46875, "min": 4187.46875, "max": 6686.52392578125, "count": 50 }, "SnowballTarget.Step.mean": { "value": 999992.0, "min": 509968.0, "max": 999992.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 999992.0, "min": 509968.0, "max": 999992.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.855216026306152, "min": 13.41816234588623, "max": 14.054774284362793, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2840.3193359375, "min": 2629.556640625, "max": 2872.60791015625, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06810875531838403, "min": 0.060986768038014366, "max": 0.07725972314576354, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.34054377659192014, "min": 0.24394707215205746, "max": 0.3862986157288177, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15498749257302752, "min": 0.14771897576603235, "max": 0.19801216610415165, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7749374628651376, "min": 0.5979825277246681, "max": 0.9198311952983632, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.521699492799996e-06, "min": 1.521699492799996e-06, "max": 0.0001483716505428, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.60849746399998e-06, "min": 7.60849746399998e-06, "max": 0.0007270082576640001, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10050719999999999, "min": 0.10050719999999999, "max": 0.1494572, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.502536, "min": 0.40598880000000004, "max": 0.7423360000000001, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.530927999999995e-05, "min": 3.530927999999995e-05, "max": 0.0024779142800000005, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00017654639999999973, "min": 0.00017654639999999973, "max": 0.0121425664, "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.Environment.CumulativeReward.mean": { "value": 27.527272727272727, "min": 25.914893617021278, "max": 27.654545454545456, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1514.0, "min": 1155.0, "max": 1521.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.527272727272727, "min": 25.914893617021278, "max": 27.654545454545456, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1514.0, "min": 1155.0, "max": 1521.0, "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": "1744794717", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744795774" }, "total": 1057.707813351, "count": 1, "self": 0.43159520499966675, "children": { "run_training.setup": { "total": 0.020902878000015335, "count": 1, "self": 0.020902878000015335 }, "TrainerController.start_learning": { "total": 1057.2553152680002, "count": 1, "self": 0.9120429370655074, "children": { "TrainerController._reset_env": { "total": 2.115488909000078, "count": 1, "self": 2.115488909000078 }, "TrainerController.advance": { "total": 1054.1408575029348, "count": 45464, "self": 0.9293232449681454, "children": { "env_step": { "total": 743.9897518249591, "count": 45464, "self": 568.0694966199433, "children": { "SubprocessEnvManager._take_step": { "total": 175.3758045239931, "count": 45464, "self": 3.1137454590088964, "children": { "TorchPolicy.evaluate": { "total": 172.26205906498421, "count": 45464, "self": 172.26205906498421 } } }, "workers": { "total": 0.5444506810226812, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1053.9592545540154, "count": 45464, "is_parallel": true, "self": 555.3718577949885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027785459999449813, "count": 1, "is_parallel": true, "self": 0.0007460490003268205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020324969996181608, "count": 10, "is_parallel": true, "self": 0.0020324969996181608 } } }, "UnityEnvironment.step": { "total": 0.03423868599998059, "count": 1, "is_parallel": true, "self": 0.0005425550002655655, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003852679999454267, "count": 1, "is_parallel": true, "self": 0.0003852679999454267 }, "communicator.exchange": { "total": 0.03154332999997678, "count": 1, "is_parallel": true, "self": 0.03154332999997678 }, "steps_from_proto": { "total": 0.0017675329997928202, "count": 1, "is_parallel": true, "self": 0.0003267340000547847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014407989997380355, "count": 10, "is_parallel": true, "self": 0.0014407989997380355 } } } } } } }, "UnityEnvironment.step": { "total": 498.5873967590269, "count": 45463, "is_parallel": true, "self": 23.904769074012847, "children": { "UnityEnvironment._generate_step_input": { "total": 13.193737811954861, "count": 45463, "is_parallel": true, "self": 13.193737811954861 }, "communicator.exchange": { "total": 385.21112384109597, "count": 45463, "is_parallel": true, "self": 385.21112384109597 }, "steps_from_proto": { "total": 76.27776603196321, "count": 45463, "is_parallel": true, "self": 13.655244054914874, "children": { "_process_rank_one_or_two_observation": { "total": 62.622521977048336, "count": 454630, "is_parallel": true, "self": 62.622521977048336 } } } } } } } } } } }, "trainer_advance": { "total": 309.22178243300755, "count": 45464, "self": 1.0819424590056315, "children": { "process_trajectory": { "total": 65.64676395300353, "count": 45464, "self": 64.64110211400452, "children": { "RLTrainer._checkpoint": { "total": 1.0056618389990035, "count": 10, "self": 1.0056618389990035 } } }, "_update_policy": { "total": 242.4930760209984, "count": 227, "self": 97.07831676199976, "children": { "TorchPPOOptimizer.update": { "total": 145.41475925899863, "count": 11574, "self": 145.41475925899863 } } } } } } }, "trainer_threads": { "total": 8.809997780190315e-07, "count": 1, "self": 8.809997780190315e-07 }, "TrainerController._save_models": { "total": 0.08692503800011764, "count": 1, "self": 0.0011586649998207577, "children": { "RLTrainer._checkpoint": { "total": 0.08576637300029688, "count": 1, "self": 0.08576637300029688 } } } } } } }