{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.953331470489502, "min": 0.953331470489502, "max": 2.870636463165283, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9112.8955078125, "min": 9112.8955078125, "max": 29429.765625, "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": 12.815046310424805, "min": 0.39998507499694824, "max": 12.815046310424805, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2498.93408203125, "min": 77.59710693359375, "max": 2560.2568359375, "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.Losses.PolicyLoss.mean": { "value": 0.07520344446432621, "min": 0.06289014027826459, "max": 0.0793365180240168, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30081377785730484, "min": 0.2561883823717853, "max": 0.3607808236516647, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18647305612616677, "min": 0.12745021336127585, "max": 0.277642860278195, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7458922245046671, "min": 0.5098008534451034, "max": 1.343410511811574, "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.CumulativeReward.mean": { "value": 25.772727272727273, "min": 3.5681818181818183, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 157.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.5681818181818183, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 157.0, "max": 1393.0, "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": "1692422537", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692423089" }, "total": 551.9532842860001, "count": 1, "self": 0.4850757430001522, "children": { "run_training.setup": { "total": 0.04497939900011261, "count": 1, "self": 0.04497939900011261 }, "TrainerController.start_learning": { "total": 551.4232291439998, "count": 1, "self": 0.6438246730072024, "children": { "TrainerController._reset_env": { "total": 4.275055437999981, "count": 1, "self": 4.275055437999981 }, "TrainerController.advance": { "total": 546.3541000189925, "count": 18202, "self": 0.3401372739749604, "children": { "env_step": { "total": 546.0139627450176, "count": 18202, "self": 398.80005628801746, "children": { "SubprocessEnvManager._take_step": { "total": 146.87747018401092, "count": 18202, "self": 2.295418662995189, "children": { "TorchPolicy.evaluate": { "total": 144.58205152101573, "count": 18202, "self": 144.58205152101573 } } }, "workers": { "total": 0.33643627298920364, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 549.2955875870061, "count": 18202, "is_parallel": true, "self": 255.8868841920057, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006893042000001515, "count": 1, "is_parallel": true, "self": 0.00515147700025409, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017415649997474247, "count": 10, "is_parallel": true, "self": 0.0017415649997474247 } } }, "UnityEnvironment.step": { "total": 0.04559610500018607, "count": 1, "is_parallel": true, "self": 0.0006507170003260399, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004061259999161848, "count": 1, "is_parallel": true, "self": 0.0004061259999161848 }, "communicator.exchange": { "total": 0.04205094000008103, "count": 1, "is_parallel": true, "self": 0.04205094000008103 }, "steps_from_proto": { "total": 0.002488321999862819, "count": 1, "is_parallel": true, "self": 0.000432052999485677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020562690003771422, "count": 10, "is_parallel": true, "self": 0.0020562690003771422 } } } } } } }, "UnityEnvironment.step": { "total": 293.40870339500043, "count": 18201, "is_parallel": true, "self": 12.039177314973585, "children": { "UnityEnvironment._generate_step_input": { "total": 6.205968351004458, "count": 18201, "is_parallel": true, "self": 6.205968351004458 }, "communicator.exchange": { "total": 230.8744561770352, "count": 18201, "is_parallel": true, "self": 230.8744561770352 }, "steps_from_proto": { "total": 44.28910155198719, "count": 18201, "is_parallel": true, "self": 8.359040725998511, "children": { "_process_rank_one_or_two_observation": { "total": 35.930060825988676, "count": 182010, "is_parallel": true, "self": 35.930060825988676 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001531870000235358, "count": 1, "self": 0.0001531870000235358, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 541.7880587390862, "count": 511826, "is_parallel": true, "self": 12.387721003074148, "children": { "process_trajectory": { "total": 296.787230455011, "count": 511826, "is_parallel": true, "self": 295.05431127401107, "children": { "RLTrainer._checkpoint": { "total": 1.732919180999943, "count": 4, "is_parallel": true, "self": 1.732919180999943 } } }, "_update_policy": { "total": 232.61310728100102, "count": 90, "is_parallel": true, "self": 95.63255078100383, "children": { "TorchPPOOptimizer.update": { "total": 136.9805564999972, "count": 4584, "is_parallel": true, "self": 136.9805564999972 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1500958270000865, "count": 1, "self": 0.0008978830001069582, "children": { "RLTrainer._checkpoint": { "total": 0.14919794399997954, "count": 1, "self": 0.14919794399997954 } } } } } } }