{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3855314552783966, "min": 0.3855314552783966, "max": 1.378066897392273, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 11498.08984375, "min": 11498.08984375, "max": 41805.0390625, "count": 40 }, "Pyramids.Step.mean": { "value": 1199954.0, "min": 29952.0, "max": 1199954.0, "count": 40 }, "Pyramids.Step.sum": { "value": 1199954.0, "min": 29952.0, "max": 1199954.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.514311671257019, "min": -0.11507374793291092, "max": 0.5285899639129639, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.86415100097656, "min": -27.617698669433594, "max": 144.83364868164062, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008747557178139687, "min": -0.0147389592602849, "max": 0.39576444029808044, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.3618404865264893, "min": -3.684739828109741, "max": 93.79617309570312, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06711962069190729, "min": 0.06521425746835857, "max": 0.07265472739878019, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.939674689686702, "min": 0.4880215411239046, "max": 1.0542681269968548, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012083479186999502, "min": 0.00010189023895286073, "max": 0.01624624423372249, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16916870861799302, "min": 0.0013245731063871895, "max": 0.22744741927211484, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.916670123047619e-06, "min": 3.916670123047619e-06, "max": 0.0002959588584899048, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.483338172266666e-05, "min": 5.483338172266666e-05, "max": 0.0035195044768319165, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10130552380952383, "min": 0.10130552380952383, "max": 0.1986529523809524, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4182773333333336, "min": 1.3905706666666668, "max": 2.5731680833333335, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001404218285714286, "min": 0.0001404218285714286, "max": 0.00986542994285714, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.0019659056, "min": 0.0019659056, "max": 0.11733949152500003, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008018297143280506, "min": 0.008018297143280506, "max": 0.569322407245636, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11225615441799164, "min": 0.11225615441799164, "max": 3.9852569103240967, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 377.8, "min": 353.6046511627907, "max": 999.0, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28335.0, "min": 15984.0, "max": 32675.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5688586429754894, "min": -1.0000000521540642, "max": 1.5998674268119557, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.6643982231617, "min": -30.56700176000595, "max": 137.5885987058282, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5688586429754894, "min": -1.0000000521540642, "max": 1.5998674268119557, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.6643982231617, "min": -30.56700176000595, "max": 137.5885987058282, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031512060582172124, "min": 0.031031723506713182, "max": 12.099198868498206, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3634045436629094, "min": 2.3634045436629094, "max": 193.5871818959713, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1748185149", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [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=PyramidsRun1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748187801" }, "total": 2651.474555421, "count": 1, "self": 0.4792221539996717, "children": { "run_training.setup": { "total": 0.019182462999992822, "count": 1, "self": 0.019182462999992822 }, "TrainerController.start_learning": { "total": 2650.976150804, "count": 1, "self": 1.624871871940286, "children": { "TrainerController._reset_env": { "total": 3.3206037840000135, "count": 1, "self": 3.3206037840000135 }, "TrainerController.advance": { "total": 2645.9451632340597, "count": 76445, "self": 1.582013245131293, "children": { "env_step": { "total": 1828.9355414649553, "count": 76445, "self": 1650.2304457689552, "children": { "SubprocessEnvManager._take_step": { "total": 177.75319938500138, "count": 76445, "self": 5.470636505054358, "children": { "TorchPolicy.evaluate": { "total": 172.28256287994702, "count": 75064, "self": 172.28256287994702 } } }, "workers": { "total": 0.9518963109986771, "count": 76445, "self": 0.0, "children": { "worker_root": { "total": 2645.403381128954, "count": 76445, "is_parallel": true, "self": 1123.4189623109519, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018121780000228682, "count": 1, "is_parallel": true, "self": 0.0005732710000074803, "children": { "_process_rank_one_or_two_observation": { "total": 0.001238907000015388, "count": 8, "is_parallel": true, "self": 0.001238907000015388 } } }, "UnityEnvironment.step": { "total": 0.04596413000001576, "count": 1, "is_parallel": true, "self": 0.0005336140000054002, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004527070000222011, "count": 1, "is_parallel": true, "self": 0.0004527070000222011 }, "communicator.exchange": { "total": 0.04333521199998813, "count": 1, "is_parallel": true, "self": 0.04333521199998813 }, "steps_from_proto": { "total": 0.0016425970000000234, "count": 1, "is_parallel": true, "self": 0.0003649190000487579, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012776779999512655, "count": 8, "is_parallel": true, "self": 0.0012776779999512655 } } } } } } }, "UnityEnvironment.step": { "total": 1521.9844188180023, "count": 76444, "is_parallel": true, "self": 37.40288924602373, "children": { "UnityEnvironment._generate_step_input": { "total": 27.334630349065947, "count": 76444, "is_parallel": true, "self": 27.334630349065947 }, "communicator.exchange": { "total": 1344.2503973670252, "count": 76444, "is_parallel": true, "self": 1344.2503973670252 }, "steps_from_proto": { "total": 112.99650185588735, "count": 76444, "is_parallel": true, "self": 22.323525861866074, "children": { "_process_rank_one_or_two_observation": { "total": 90.67297599402127, "count": 611552, "is_parallel": true, "self": 90.67297599402127 } } } } } } } } } } }, "trainer_advance": { "total": 815.4276085239729, "count": 76445, "self": 3.035592685941424, "children": { "process_trajectory": { "total": 151.7309350920292, "count": 76445, "self": 151.39702853002916, "children": { "RLTrainer._checkpoint": { "total": 0.3339065620000383, "count": 2, "self": 0.3339065620000383 } } }, "_update_policy": { "total": 660.6610807460023, "count": 535, "self": 366.8418774560113, "children": { "TorchPPOOptimizer.update": { "total": 293.81920328999104, "count": 27378, "self": 293.81920328999104 } } } } } } }, "trainer_threads": { "total": 8.179999895219225e-07, "count": 1, "self": 8.179999895219225e-07 }, "TrainerController._save_models": { "total": 0.08551109600011841, "count": 1, "self": 0.001321020000432327, "children": { "RLTrainer._checkpoint": { "total": 0.08419007599968609, "count": 1, "self": 0.08419007599968609 } } } } } } }