{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5057324767112732, "min": 0.4924047887325287, "max": 1.4576853513717651, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15212.43359375, "min": 14590.9384765625, "max": 44220.34375, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4942851960659027, "min": -0.16911569237709045, "max": 0.5614364147186279, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.45700073242188, "min": -40.08041763305664, "max": 154.95645141601562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025497764348983765, "min": -0.03437432274222374, "max": 0.20318932831287384, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.884396553039551, "min": -9.28106689453125, "max": 48.765438079833984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06786938469652518, "min": 0.0639943620959197, "max": 0.07500730357525585, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9501713857513525, "min": 0.4973396148269022, "max": 1.070313481313254, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013230102525108313, "min": 0.00047396930166166605, "max": 0.01541516824848562, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1852214353515164, "min": 0.006161600921601658, "max": 0.21581235547879868, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3454261229857106e-06, "min": 7.3454261229857106e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010283596572179995, "min": 0.00010283596572179995, "max": 0.0033745093751636, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244844285714286, "min": 0.10244844285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342782, "min": 1.3886848, "max": 2.5275201, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025459944142857126, "min": 0.00025459944142857126, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003564392179999998, "min": 0.003564392179999998, "max": 0.11250115635999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007546940352767706, "min": 0.007213592994958162, "max": 0.3259185254573822, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1056571677327156, "min": 0.10099030286073685, "max": 2.2814297676086426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 368.48, "min": 365.8292682926829, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27636.0, "min": 15984.0, "max": 32785.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.551493307352066, "min": -1.0000000521540642, "max": 1.6030684711590206, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 116.36199805140495, "min": -30.353001683950424, "max": 133.9431977942586, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.551493307352066, "min": -1.0000000521540642, "max": 1.6030684711590206, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 116.36199805140495, "min": -30.353001683950424, "max": 133.9431977942586, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028932002410292625, "min": 0.028209994182372924, "max": 5.96291976980865, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.169900180771947, "min": 2.169900180771947, "max": 95.4067163169384, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715407587", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=ppo_pyramids_rnd --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715410187" }, "total": 2600.2033352189997, "count": 1, "self": 0.7309419489997708, "children": { "run_training.setup": { "total": 0.08204079600000114, "count": 1, "self": 0.08204079600000114 }, "TrainerController.start_learning": { "total": 2599.390352474, "count": 1, "self": 1.8862149269962174, "children": { "TrainerController._reset_env": { "total": 3.72560424400001, "count": 1, "self": 3.72560424400001 }, "TrainerController.advance": { "total": 2593.6898067660036, "count": 63809, "self": 2.0153385299890942, "children": { "env_step": { "total": 1858.0294217060043, "count": 63809, "self": 1691.4037397100578, "children": { "SubprocessEnvManager._take_step": { "total": 165.39009754897677, "count": 63809, "self": 6.012274990939886, "children": { "TorchPolicy.evaluate": { "total": 159.37782255803688, "count": 62556, "self": 159.37782255803688 } } }, "workers": { "total": 1.2355844469696535, "count": 63809, "self": 0.0, "children": { "worker_root": { "total": 2593.5158943059732, "count": 63809, "is_parallel": true, "self": 1056.475909569967, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005487153999979455, "count": 1, "is_parallel": true, "self": 0.004009238999799436, "children": { "_process_rank_one_or_two_observation": { "total": 0.001477915000180019, "count": 8, "is_parallel": true, "self": 0.001477915000180019 } } }, "UnityEnvironment.step": { "total": 0.08112022199998137, "count": 1, "is_parallel": true, "self": 0.0007306419999508762, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004953850000219973, "count": 1, "is_parallel": true, "self": 0.0004953850000219973 }, "communicator.exchange": { "total": 0.07807850299997199, "count": 1, "is_parallel": true, "self": 0.07807850299997199 }, "steps_from_proto": { "total": 0.0018156920000365062, "count": 1, "is_parallel": true, "self": 0.0003612470000007306, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014544450000357756, "count": 8, "is_parallel": true, "self": 0.0014544450000357756 } } } } } } }, "UnityEnvironment.step": { "total": 1537.0399847360063, "count": 63808, "is_parallel": true, "self": 43.21973356797707, "children": { "UnityEnvironment._generate_step_input": { "total": 26.7130082210208, "count": 63808, "is_parallel": true, "self": 26.7130082210208 }, "communicator.exchange": { "total": 1349.7444897019914, "count": 63808, "is_parallel": true, "self": 1349.7444897019914 }, "steps_from_proto": { "total": 117.36275324501702, "count": 63808, "is_parallel": true, "self": 24.999386948192353, "children": { "_process_rank_one_or_two_observation": { "total": 92.36336629682467, "count": 510464, "is_parallel": true, "self": 92.36336629682467 } } } } } } } } } } }, "trainer_advance": { "total": 733.6450465300103, "count": 63809, "self": 3.733232432970567, "children": { "process_trajectory": { "total": 148.18063105103994, "count": 63809, "self": 147.8965525350398, "children": { "RLTrainer._checkpoint": { "total": 0.284078516000136, "count": 2, "self": 0.284078516000136 } } }, "_update_policy": { "total": 581.7311830459998, "count": 450, "self": 343.4766840350021, "children": { "TorchPPOOptimizer.update": { "total": 238.25449901099773, "count": 22860, "self": 238.25449901099773 } } } } } } }, "trainer_threads": { "total": 7.749999895168003e-07, "count": 1, "self": 7.749999895168003e-07 }, "TrainerController._save_models": { "total": 0.08872576200019466, "count": 1, "self": 0.0014940290002414258, "children": { "RLTrainer._checkpoint": { "total": 0.08723173299995324, "count": 1, "self": 0.08723173299995324 } } } } } } }