{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9775559902191162, "min": 0.9775559902191162, "max": 2.872464418411255, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9376.716796875, "min": 9376.716796875, "max": 29511.69921875, "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": 11.800005912780762, "min": 0.45459917187690735, "max": 11.800005912780762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2301.001220703125, "min": 88.1922378540039, "max": 2389.35400390625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06591380340422107, "min": 0.06238260831114353, "max": 0.07292379539884518, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26365521361688427, "min": 0.2495304332445741, "max": 0.3643843538913072, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18324272849542253, "min": 0.12359145098918245, "max": 0.2624319669078378, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7329709139816901, "min": 0.4943658039567298, "max": 1.3121598345391892, "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": 23.431818181818183, "min": 3.477272727272727, "max": 23.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1031.0, "min": 153.0, "max": 1267.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.431818181818183, "min": 3.477272727272727, "max": 23.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1031.0, "min": 153.0, "max": 1267.0, "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": "1679570613", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679571061" }, "total": 448.139563646, "count": 1, "self": 0.39128738200003, "children": { "run_training.setup": { "total": 0.16369366099996796, "count": 1, "self": 0.16369366099996796 }, "TrainerController.start_learning": { "total": 447.584582603, "count": 1, "self": 0.5110639409967348, "children": { "TrainerController._reset_env": { "total": 8.639746959000036, "count": 1, "self": 8.639746959000036 }, "TrainerController.advance": { "total": 438.2433231400032, "count": 18221, "self": 0.2742121180127697, "children": { "env_step": { "total": 437.96911102199044, "count": 18221, "self": 316.9103597230044, "children": { "SubprocessEnvManager._take_step": { "total": 120.80043758299684, "count": 18221, "self": 2.002225890998659, "children": { "TorchPolicy.evaluate": { "total": 118.79821169199818, "count": 18221, "self": 118.79821169199818 } } }, "workers": { "total": 0.2583137159892317, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 446.2314490729993, "count": 18221, "is_parallel": true, "self": 212.74635236100642, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006738719999987097, "count": 1, "is_parallel": true, "self": 0.004207532999942032, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025311870000450654, "count": 10, "is_parallel": true, "self": 0.0025311870000450654 } } }, "UnityEnvironment.step": { "total": 0.043920142000047235, "count": 1, "is_parallel": true, "self": 0.0005726260000074035, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033999700002596, "count": 1, "is_parallel": true, "self": 0.00033999700002596 }, "communicator.exchange": { "total": 0.041269881999994595, "count": 1, "is_parallel": true, "self": 0.041269881999994595 }, "steps_from_proto": { "total": 0.0017376370000192765, "count": 1, "is_parallel": true, "self": 0.00038744700003690014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013501899999823763, "count": 10, "is_parallel": true, "self": 0.0013501899999823763 } } } } } } }, "UnityEnvironment.step": { "total": 233.48509671199287, "count": 18220, "is_parallel": true, "self": 9.336752488989475, "children": { "UnityEnvironment._generate_step_input": { "total": 5.014934349001237, "count": 18220, "is_parallel": true, "self": 5.014934349001237 }, "communicator.exchange": { "total": 189.32785642800377, "count": 18220, "is_parallel": true, "self": 189.32785642800377 }, "steps_from_proto": { "total": 29.805553445998385, "count": 18220, "is_parallel": true, "self": 5.872342796015857, "children": { "_process_rank_one_or_two_observation": { "total": 23.933210649982527, "count": 182200, "is_parallel": true, "self": 23.933210649982527 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011030300004222227, "count": 1, "self": 0.00011030300004222227, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 434.9669827660015, "count": 395490, "is_parallel": true, "self": 9.47991973898013, "children": { "process_trajectory": { "total": 242.74105078902096, "count": 395490, "is_parallel": true, "self": 241.16653504402097, "children": { "RLTrainer._checkpoint": { "total": 1.5745157449999851, "count": 4, "is_parallel": true, "self": 1.5745157449999851 } } }, "_update_policy": { "total": 182.7460122380004, "count": 90, "is_parallel": true, "self": 65.70358981400199, "children": { "TorchPPOOptimizer.update": { "total": 117.0424224239984, "count": 4587, "is_parallel": true, "self": 117.0424224239984 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1903382599999759, "count": 1, "self": 0.0008359149999250803, "children": { "RLTrainer._checkpoint": { "total": 0.1895023450000508, "count": 1, "self": 0.1895023450000508 } } } } } } }