{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6614677309989929, "min": 0.624437153339386, "max": 1.4495316743850708, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20066.28515625, "min": 18623.212890625, "max": 43972.9921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.17816321551799774, "min": -0.09843263775110245, "max": 0.24956122040748596, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 45.96611022949219, "min": -23.62383270263672, "max": 64.38679504394531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04464343190193176, "min": 0.014565401710569859, "max": 0.42815732955932617, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.51800537109375, "min": 3.75787353515625, "max": 101.4732894897461, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06673291528464428, "min": 0.06385992573149367, "max": 0.07487885772154966, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.93426081398502, "min": 0.5028726533774538, "max": 1.0483040081016952, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013219503633774278, "min": 5.7436506656377785e-05, "max": 0.013219503633774278, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1850730508728399, "min": 0.000804111093189289, "max": 0.1850730508728399, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.614933176007141e-06, "min": 7.614933176007141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010660906446409997, "min": 0.00010660906446409997, "max": 0.0034940305353231994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253827857142858, "min": 0.10253827857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355359, "min": 1.3691136000000002, "max": 2.4646767999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026357402928571424, "min": 0.00026357402928571424, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003690036409999999, "min": 0.003690036409999999, "max": 0.11648121232000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0158916674554348, "min": 0.014994309283792973, "max": 0.5486355423927307, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2224833369255066, "min": 0.20992033183574677, "max": 3.8404488563537598, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 594.0566037735849, "min": 594.0566037735849, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31485.0, "min": 15984.0, "max": 32936.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9907207171309669, "min": -1.0000000521540642, "max": 1.0021450662729787, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 52.508198007941246, "min": -32.000001668930054, "max": 52.508198007941246, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9907207171309669, "min": -1.0000000521540642, "max": 1.0021450662729787, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 52.508198007941246, "min": -32.000001668930054, "max": 52.508198007941246, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09674923490504471, "min": 0.09674923490504471, "max": 11.81224724277854, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.127709449967369, "min": 4.499935531057417, "max": 188.99595588445663, "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": "1714116828", "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=Pyramids Training --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": "1714119890" }, "total": 3062.287625334, "count": 1, "self": 0.65410189000022, "children": { "run_training.setup": { "total": 0.087654821000001, "count": 1, "self": 0.087654821000001 }, "TrainerController.start_learning": { "total": 3061.545868623, "count": 1, "self": 2.2441152770070403, "children": { "TrainerController._reset_env": { "total": 4.225094906999971, "count": 1, "self": 4.225094906999971 }, "TrainerController.advance": { "total": 3054.989217508993, "count": 63332, "self": 2.5817324849608667, "children": { "env_step": { "total": 2020.3300071510266, "count": 63332, "self": 1861.6892714400128, "children": { "SubprocessEnvManager._take_step": { "total": 157.22398245807676, "count": 63332, "self": 6.824593044162384, "children": { "TorchPolicy.evaluate": { "total": 150.39938941391438, "count": 62566, "self": 150.39938941391438 } } }, "workers": { "total": 1.4167532529371556, "count": 63332, "self": 0.0, "children": { "worker_root": { "total": 3054.1762206250282, "count": 63332, "is_parallel": true, "self": 1374.7828476889988, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008965269999976044, "count": 1, "is_parallel": true, "self": 0.006739219999985835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022260499999902095, "count": 8, "is_parallel": true, "self": 0.0022260499999902095 } } }, "UnityEnvironment.step": { "total": 0.09563753400004771, "count": 1, "is_parallel": true, "self": 0.0007888110000067172, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005246489999990445, "count": 1, "is_parallel": true, "self": 0.0005246489999990445 }, "communicator.exchange": { "total": 0.09065382100004626, "count": 1, "is_parallel": true, "self": 0.09065382100004626 }, "steps_from_proto": { "total": 0.0036702529999956823, "count": 1, "is_parallel": true, "self": 0.0020254469998235436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016448060001721387, "count": 8, "is_parallel": true, "self": 0.0016448060001721387 } } } } } } }, "UnityEnvironment.step": { "total": 1679.3933729360294, "count": 63331, "is_parallel": true, "self": 51.37976593402777, "children": { "UnityEnvironment._generate_step_input": { "total": 31.00340303296923, "count": 63331, "is_parallel": true, "self": 31.00340303296923 }, "communicator.exchange": { "total": 1464.5999816950332, "count": 63331, "is_parallel": true, "self": 1464.5999816950332 }, "steps_from_proto": { "total": 132.41022227399924, "count": 63331, "is_parallel": true, "self": 28.64218533688245, "children": { "_process_rank_one_or_two_observation": { "total": 103.76803693711679, "count": 506648, "is_parallel": true, "self": 103.76803693711679 } } } } } } } } } } }, "trainer_advance": { "total": 1032.0774778730056, "count": 63332, "self": 4.391738416962653, "children": { "process_trajectory": { "total": 158.54828890603847, "count": 63332, "self": 158.30263998103862, "children": { "RLTrainer._checkpoint": { "total": 0.24564892499984126, "count": 2, "self": 0.24564892499984126 } } }, "_update_policy": { "total": 869.1374505500045, "count": 446, "self": 356.568977969986, "children": { "TorchPPOOptimizer.update": { "total": 512.5684725800185, "count": 22857, "self": 512.5684725800185 } } } } } } }, "trainer_threads": { "total": 1.2629998309421353e-06, "count": 1, "self": 1.2629998309421353e-06 }, "TrainerController._save_models": { "total": 0.08743966700012606, "count": 1, "self": 0.0022515660002682125, "children": { "RLTrainer._checkpoint": { "total": 0.08518810099985785, "count": 1, "self": 0.08518810099985785 } } } } } } }