{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0629947185516357, "min": 1.0629947185516357, "max": 2.853997230529785, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10184.552734375, "min": 10184.552734375, "max": 29196.390625, "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": 12.772660255432129, "min": 0.32505810260772705, "max": 12.772660255432129, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2490.668701171875, "min": 63.06127166748047, "max": 2575.4423828125, "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": 0.06789310773213704, "min": 0.06398406166619822, "max": 0.0741560998415248, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27157243092854816, "min": 0.26814070572921384, "max": 0.370780499207624, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22101247668558477, "min": 0.12968356727951152, "max": 0.29254896214195325, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8840499067423391, "min": 0.5187342691180461, "max": 1.4627448107097663, "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": 24.727272727272727, "min": 3.3863636363636362, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1088.0, "min": 149.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.3863636363636362, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1088.0, "min": 149.0, "max": 1402.0, "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": "1686243726", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1686244237" }, "total": 511.11260580399994, "count": 1, "self": 0.4240298010004153, "children": { "run_training.setup": { "total": 0.06239056899994466, "count": 1, "self": 0.06239056899994466 }, "TrainerController.start_learning": { "total": 510.6261854339996, "count": 1, "self": 0.6536907369654728, "children": { "TrainerController._reset_env": { "total": 4.452576729000157, "count": 1, "self": 4.452576729000157 }, "TrainerController.advance": { "total": 505.38064967303353, "count": 18206, "self": 0.3011227710130697, "children": { "env_step": { "total": 505.07952690202046, "count": 18206, "self": 365.8526361849749, "children": { "SubprocessEnvManager._take_step": { "total": 138.92391830501765, "count": 18206, "self": 2.1226161180361487, "children": { "TorchPolicy.evaluate": { "total": 136.8013021869815, "count": 18206, "self": 136.8013021869815 } } }, "workers": { "total": 0.3029724120278843, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 508.704357688001, "count": 18206, "is_parallel": true, "self": 239.90498363299866, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029386770002020057, "count": 1, "is_parallel": true, "self": 0.0007997269995030365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021389500006989692, "count": 10, "is_parallel": true, "self": 0.0021389500006989692 } } }, "UnityEnvironment.step": { "total": 0.03543703600007575, "count": 1, "is_parallel": true, "self": 0.0005874520002180361, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003256830000282207, "count": 1, "is_parallel": true, "self": 0.0003256830000282207 }, "communicator.exchange": { "total": 0.03243442999973922, "count": 1, "is_parallel": true, "self": 0.03243442999973922 }, "steps_from_proto": { "total": 0.0020894710000902705, "count": 1, "is_parallel": true, "self": 0.0003781969999181456, "children": { "_process_rank_one_or_two_observation": { "total": 0.001711274000172125, "count": 10, "is_parallel": true, "self": 0.001711274000172125 } } } } } } }, "UnityEnvironment.step": { "total": 268.7993740550023, "count": 18205, "is_parallel": true, "self": 10.983437682008116, "children": { "UnityEnvironment._generate_step_input": { "total": 6.014158724961817, "count": 18205, "is_parallel": true, "self": 6.014158724961817 }, "communicator.exchange": { "total": 212.79225344901624, "count": 18205, "is_parallel": true, "self": 212.79225344901624 }, "steps_from_proto": { "total": 39.00952419901614, "count": 18205, "is_parallel": true, "self": 7.171393315178193, "children": { "_process_rank_one_or_two_observation": { "total": 31.838130883837948, "count": 182050, "is_parallel": true, "self": 31.838130883837948 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015679300031479215, "count": 1, "self": 0.00015679300031479215, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 501.3334425659041, "count": 485821, "is_parallel": true, "self": 10.938737156138814, "children": { "process_trajectory": { "total": 275.0488894597638, "count": 485821, "is_parallel": true, "self": 273.68149758576374, "children": { "RLTrainer._checkpoint": { "total": 1.3673918740000772, "count": 4, "is_parallel": true, "self": 1.3673918740000772 } } }, "_update_policy": { "total": 215.34581595000145, "count": 90, "is_parallel": true, "self": 84.47682597000312, "children": { "TorchPPOOptimizer.update": { "total": 130.86898997999833, "count": 4584, "is_parallel": true, "self": 130.86898997999833 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13911150200010525, "count": 1, "self": 0.0008934269999372191, "children": { "RLTrainer._checkpoint": { "total": 0.13821807500016803, "count": 1, "self": 0.13821807500016803 } } } } } } }