{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9023377895355225, "min": 0.9023377895355225, "max": 2.8594303131103516, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8615.521484375, "min": 8615.521484375, "max": 29314.87890625, "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": 12.87948226928711, "min": 0.5008751153945923, "max": 12.87948226928711, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.4990234375, "min": 97.16976928710938, "max": 2622.58349609375, "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": 0.06644343368323319, "min": 0.06235570924678434, "max": 0.0723133066020833, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26577373473293275, "min": 0.24942283698713735, "max": 0.36076364907271724, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21021952286508738, "min": 0.11854346034085086, "max": 0.2798754612312597, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8408780914603495, "min": 0.47417384136340346, "max": 1.3017513816263162, "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": 25.045454545454547, "min": 3.227272727272727, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 142.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.227272727272727, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 142.0, "max": 1374.0, "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": "1719676652", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719677109" }, "total": 457.658923092, "count": 1, "self": 0.4411386090000633, "children": { "run_training.setup": { "total": 0.05887648300000592, "count": 1, "self": 0.05887648300000592 }, "TrainerController.start_learning": { "total": 457.15890799999994, "count": 1, "self": 0.5745242849962438, "children": { "TrainerController._reset_env": { "total": 2.882802285000025, "count": 1, "self": 2.882802285000025 }, "TrainerController.advance": { "total": 453.61135217100366, "count": 18202, "self": 0.27706798100717833, "children": { "env_step": { "total": 453.3342841899965, "count": 18202, "self": 296.3218845829938, "children": { "SubprocessEnvManager._take_step": { "total": 156.72464404800445, "count": 18202, "self": 1.5039967240015812, "children": { "TorchPolicy.evaluate": { "total": 155.22064732400287, "count": 18202, "self": 155.22064732400287 } } }, "workers": { "total": 0.2877555589982421, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 456.0355911930079, "count": 18202, "is_parallel": true, "self": 230.089937936998, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008367338000027758, "count": 1, "is_parallel": true, "self": 0.006716204999918318, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016511330001094393, "count": 10, "is_parallel": true, "self": 0.0016511330001094393 } } }, "UnityEnvironment.step": { "total": 0.04696652199999107, "count": 1, "is_parallel": true, "self": 0.0007671759999539063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038777400004619267, "count": 1, "is_parallel": true, "self": 0.00038777400004619267 }, "communicator.exchange": { "total": 0.043834231000005275, "count": 1, "is_parallel": true, "self": 0.043834231000005275 }, "steps_from_proto": { "total": 0.0019773409999856995, "count": 1, "is_parallel": true, "self": 0.0004127899999843976, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015645510000013019, "count": 10, "is_parallel": true, "self": 0.0015645510000013019 } } } } } } }, "UnityEnvironment.step": { "total": 225.9456532560099, "count": 18201, "is_parallel": true, "self": 10.237274953992198, "children": { "UnityEnvironment._generate_step_input": { "total": 5.486850761006735, "count": 18201, "is_parallel": true, "self": 5.486850761006735 }, "communicator.exchange": { "total": 176.08001943400154, "count": 18201, "is_parallel": true, "self": 176.08001943400154 }, "steps_from_proto": { "total": 34.14150810700943, "count": 18201, "is_parallel": true, "self": 6.523216121010819, "children": { "_process_rank_one_or_two_observation": { "total": 27.61829198599861, "count": 182010, "is_parallel": true, "self": 27.61829198599861 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001949369999465489, "count": 1, "self": 0.0001949369999465489, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 447.97396249001895, "count": 678543, "is_parallel": true, "self": 14.14382557704863, "children": { "process_trajectory": { "total": 246.58530576197057, "count": 678543, "is_parallel": true, "self": 245.8671063269706, "children": { "RLTrainer._checkpoint": { "total": 0.7181994349999741, "count": 4, "is_parallel": true, "self": 0.7181994349999741 } } }, "_update_policy": { "total": 187.24483115099974, "count": 90, "is_parallel": true, "self": 61.04056360699849, "children": { "TorchPPOOptimizer.update": { "total": 126.20426754400125, "count": 4587, "is_parallel": true, "self": 126.20426754400125 } } } } } } } } }, "TrainerController._save_models": { "total": 0.090034322000065, "count": 1, "self": 0.0009265810000442798, "children": { "RLTrainer._checkpoint": { "total": 0.08910774100002072, "count": 1, "self": 0.08910774100002072 } } } } } } }