{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8223253488540649, "min": 0.799433708190918, "max": 2.8630354404449463, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7932.97265625, "min": 7606.61181640625, "max": 29351.83984375, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.931161880493164, "min": 0.45234382152557373, "max": 13.931161880493164, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2855.88818359375, "min": 87.75469970703125, "max": 2855.88818359375, "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.Losses.PolicyLoss.mean": { "value": 0.07091916145747709, "min": 0.06246914924715883, "max": 0.07817078895439444, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3545958072873855, "min": 0.2524322550515553, "max": 0.3908539447719722, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17772815060966157, "min": 0.11347350857777558, "max": 0.2661994262653239, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8886407530483078, "min": 0.4538940343111023, "max": 1.3309971313266193, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.5616989824000025e-06, "min": 3.5616989824000025e-06, "max": 0.0003462116010824, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.7808494912000013e-05, "min": 1.7808494912000013e-05, "max": 0.0016964080153120003, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.181818181818183, "min": 3.272727272727273, "max": 27.545454545454547, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1495.0, "min": 144.0, "max": 1515.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.181818181818183, "min": 3.272727272727273, "max": 27.545454545454547, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1495.0, "min": 144.0, "max": 1515.0, "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": "1717143340", "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.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "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": "1717144426" }, "total": 1085.99541931, "count": 1, "self": 0.43473192800001925, "children": { "run_training.setup": { "total": 0.055542580000064845, "count": 1, "self": 0.055542580000064845 }, "TrainerController.start_learning": { "total": 1085.505144802, "count": 1, "self": 1.3018926839840788, "children": { "TrainerController._reset_env": { "total": 2.052020551999931, "count": 1, "self": 2.052020551999931 }, "TrainerController.advance": { "total": 1082.0634089470161, "count": 45476, "self": 0.6114708699622042, "children": { "env_step": { "total": 1081.451938077054, "count": 45476, "self": 700.7580134160967, "children": { "SubprocessEnvManager._take_step": { "total": 380.047344059956, "count": 45476, "self": 3.480147482963048, "children": { "TorchPolicy.evaluate": { "total": 376.56719657699296, "count": 45476, "self": 376.56719657699296 } } }, "workers": { "total": 0.6465806010012329, "count": 45476, "self": 0.0, "children": { "worker_root": { "total": 1082.516006696951, "count": 45476, "is_parallel": true, "self": 547.2498122079307, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002331701000002795, "count": 1, "is_parallel": true, "self": 0.0006857359999230539, "children": { "_process_rank_one_or_two_observation": { "total": 0.001645965000079741, "count": 10, "is_parallel": true, "self": 0.001645965000079741 } } }, "UnityEnvironment.step": { "total": 0.03653775800012227, "count": 1, "is_parallel": true, "self": 0.000707356000020809, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004187240001556347, "count": 1, "is_parallel": true, "self": 0.0004187240001556347 }, "communicator.exchange": { "total": 0.033396798000012495, "count": 1, "is_parallel": true, "self": 0.033396798000012495 }, "steps_from_proto": { "total": 0.0020148799999333278, "count": 1, "is_parallel": true, "self": 0.00039830099990467716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016165790000286506, "count": 10, "is_parallel": true, "self": 0.0016165790000286506 } } } } } } }, "UnityEnvironment.step": { "total": 535.2661944890203, "count": 45475, "is_parallel": true, "self": 24.71541623496114, "children": { "UnityEnvironment._generate_step_input": { "total": 12.955120059065848, "count": 45475, "is_parallel": true, "self": 12.955120059065848 }, "communicator.exchange": { "total": 416.1775510239354, "count": 45475, "is_parallel": true, "self": 416.1775510239354 }, "steps_from_proto": { "total": 81.41810717105795, "count": 45475, "is_parallel": true, "self": 15.309917971942241, "children": { "_process_rank_one_or_two_observation": { "total": 66.10818919911571, "count": 454750, "is_parallel": true, "self": 66.10818919911571 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001737859997774649, "count": 1, "self": 0.0001737859997774649, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1068.9248886532941, "count": 1648536, "is_parallel": true, "self": 34.946814295369904, "children": { "process_trajectory": { "total": 588.2397075129222, "count": 1648536, "is_parallel": true, "self": 586.5158492779219, "children": { "RLTrainer._checkpoint": { "total": 1.723858235000307, "count": 10, "is_parallel": true, "self": 1.723858235000307 } } }, "_update_policy": { "total": 445.738366845002, "count": 227, "is_parallel": true, "self": 141.80564636297345, "children": { "TorchPPOOptimizer.update": { "total": 303.93272048202857, "count": 11571, "is_parallel": true, "self": 303.93272048202857 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08764883300000292, "count": 1, "self": 0.0012193009997645277, "children": { "RLTrainer._checkpoint": { "total": 0.0864295320002384, "count": 1, "self": 0.0864295320002384 } } } } } } }