{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7719730138778687, "min": 0.7613688111305237, "max": 2.8716540336608887, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7931.2509765625, "min": 7360.3984375, "max": 29440.197265625, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.31866455078125, "min": 0.4299190640449524, "max": 13.31866455078125, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2717.007568359375, "min": 83.404296875, "max": 2717.007568359375, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07006980144634486, "min": 0.062026680194699736, "max": 0.07465941691400219, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35034900723172435, "min": 0.2547798439890019, "max": 0.3702042288051041, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17959184634919262, "min": 0.10945015278868561, "max": 0.27307484038904606, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.897959231745963, "min": 0.43780061115474245, "max": 1.3653742019452302, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.288098237333331e-06, "min": 5.288098237333331e-06, "max": 0.00029458800180399996, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.6440491186666655e-05, "min": 2.6440491186666655e-05, "max": 0.0014234400255199997, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.12727272727273, "min": 3.2045454545454546, "max": 26.613636363636363, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1437.0, "min": 141.0, "max": 1437.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.12727272727273, "min": 3.2045454545454546, "max": 26.613636363636363, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1437.0, "min": 141.0, "max": 1437.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677356105", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677356856" }, "total": 750.599613773, "count": 1, "self": 0.7898734890001151, "children": { "run_training.setup": { "total": 0.26667985099999214, "count": 1, "self": 0.26667985099999214 }, "TrainerController.start_learning": { "total": 749.5430604329999, "count": 1, "self": 0.9755000639958098, "children": { "TrainerController._reset_env": { "total": 8.884632754000023, "count": 1, "self": 8.884632754000023 }, "TrainerController.advance": { "total": 739.4709153560041, "count": 27346, "self": 0.490108629997394, "children": { "env_step": { "total": 738.9808067260067, "count": 27346, "self": 514.3572279820039, "children": { "SubprocessEnvManager._take_step": { "total": 224.15215424599933, "count": 27346, "self": 2.5170199669947806, "children": { "TorchPolicy.evaluate": { "total": 221.63513427900455, "count": 27346, "self": 49.60262820800682, "children": { "TorchPolicy.sample_actions": { "total": 172.03250607099773, "count": 27346, "self": 172.03250607099773 } } } } }, "workers": { "total": 0.4714244980035005, "count": 27346, "self": 0.0, "children": { "worker_root": { "total": 747.0872799079963, "count": 27346, "is_parallel": true, "self": 355.6644734749943, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0069400369999925715, "count": 1, "is_parallel": true, "self": 0.003068791000004012, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038712459999885596, "count": 10, "is_parallel": true, "self": 0.0038712459999885596 } } }, "UnityEnvironment.step": { "total": 0.04245620700004338, "count": 1, "is_parallel": true, "self": 0.0006708650000746275, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040243999995936974, "count": 1, "is_parallel": true, "self": 0.00040243999995936974 }, "communicator.exchange": { "total": 0.03905654800001912, "count": 1, "is_parallel": true, "self": 0.03905654800001912 }, "steps_from_proto": { "total": 0.0023263539999902605, "count": 1, "is_parallel": true, "self": 0.0005173690000219722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018089849999682883, "count": 10, "is_parallel": true, "self": 0.0018089849999682883 } } } } } } }, "UnityEnvironment.step": { "total": 391.422806433002, "count": 27345, "is_parallel": true, "self": 15.326766209005598, "children": { "UnityEnvironment._generate_step_input": { "total": 8.690558491004367, "count": 27345, "is_parallel": true, "self": 8.690558491004367 }, "communicator.exchange": { "total": 315.1374482329929, "count": 27345, "is_parallel": true, "self": 315.1374482329929 }, "steps_from_proto": { "total": 52.26803349999915, "count": 27345, "is_parallel": true, "self": 12.144349741025962, "children": { "_process_rank_one_or_two_observation": { "total": 40.123683758973186, "count": 273450, "is_parallel": true, "self": 40.123683758973186 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013262300001315452, "count": 1, "self": 0.00013262300001315452, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 734.0769342169971, "count": 639758, "is_parallel": true, "self": 16.782281365958056, "children": { "process_trajectory": { "total": 420.32285520103886, "count": 639758, "is_parallel": true, "self": 417.6905910570387, "children": { "RLTrainer._checkpoint": { "total": 2.632264144000146, "count": 6, "is_parallel": true, "self": 2.632264144000146 } } }, "_update_policy": { "total": 296.9717976500002, "count": 136, "is_parallel": true, "self": 105.62118091000394, "children": { "TorchPPOOptimizer.update": { "total": 191.35061673999627, "count": 6933, "is_parallel": true, "self": 191.35061673999627 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21187963600004878, "count": 1, "self": 0.001226135000024442, "children": { "RLTrainer._checkpoint": { "total": 0.21065350100002433, "count": 1, "self": 0.21065350100002433 } } } } } } }