{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5393688082695007, "min": 0.5393688082695007, "max": 1.4367049932479858, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16267.36328125, "min": 16165.83984375, "max": 43583.8828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2346208542585373, "min": -0.1154862493276596, "max": 0.2346208542585373, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 60.06293869018555, "min": -27.832185745239258, "max": 60.06293869018555, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009887306950986385, "min": -0.0593528226017952, "max": 0.25042131543159485, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.5311505794525146, "min": -15.313028335571289, "max": 59.349849700927734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0679244632882109, "min": 0.06437890143857626, "max": 0.07401963903523685, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9509424860349527, "min": 0.5130843374334229, "max": 1.0362749464933159, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00973741925242778, "min": 0.00010476516669533935, "max": 0.011923536809686072, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13632386953398892, "min": 0.0013619471670394117, "max": 0.16692951533560502, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3561404051285725e-06, "min": 7.3561404051285725e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010298596567180002, "min": 0.00010298596567180002, "max": 0.0034932235355922, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024520142857143, "min": 0.1024520142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343282000000002, "min": 1.3886848, "max": 2.527323, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025495622714285707, "min": 0.00025495622714285707, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035693871799999987, "min": 0.0035693871799999987, "max": 0.11645433922000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009274216368794441, "min": 0.00925131980329752, "max": 0.44898343086242676, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12983903288841248, "min": 0.12983903288841248, "max": 3.1428840160369873, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 654.8958333333334, "min": 588.1063829787234, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31435.0, "min": 15984.0, "max": 34229.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7615916295908391, "min": -1.0000000521540642, "max": 1.0543646772994715, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 36.55639822036028, "min": -31.990001633763313, "max": 53.772598542273045, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7615916295908391, "min": -1.0000000521540642, "max": 1.0543646772994715, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 36.55639822036028, "min": -31.990001633763313, "max": 53.772598542273045, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0625008533570508, "min": 0.05931555827841044, "max": 9.101365353912115, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0000409611384384, "min": 2.8451240608119406, "max": 145.62184566259384, "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": "1739111493", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --force --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739113650" }, "total": 2156.3099500759995, "count": 1, "self": 0.9323350109989406, "children": { "run_training.setup": { "total": 0.01992140099991957, "count": 1, "self": 0.01992140099991957 }, "TrainerController.start_learning": { "total": 2155.3576936640006, "count": 1, "self": 1.3583075390324666, "children": { "TrainerController._reset_env": { "total": 2.0549091459997726, "count": 1, "self": 2.0549091459997726 }, "TrainerController.advance": { "total": 2151.8158757509677, "count": 63249, "self": 1.3746821409736185, "children": { "env_step": { "total": 1466.867355139986, "count": 63249, "self": 1312.1103283211887, "children": { "SubprocessEnvManager._take_step": { "total": 153.99819530189325, "count": 63249, "self": 4.684525093892262, "children": { "TorchPolicy.evaluate": { "total": 149.31367020800099, "count": 62565, "self": 149.31367020800099 } } }, "workers": { "total": 0.758831516904138, "count": 63249, "self": 0.0, "children": { "worker_root": { "total": 2150.14690566695, "count": 63249, "is_parallel": true, "self": 951.281361478937, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019293060004201834, "count": 1, "is_parallel": true, "self": 0.0006385970000337693, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012907090003864141, "count": 8, "is_parallel": true, "self": 0.0012907090003864141 } } }, "UnityEnvironment.step": { "total": 0.05057443699979558, "count": 1, "is_parallel": true, "self": 0.0005235670000729442, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000491064999550872, "count": 1, "is_parallel": true, "self": 0.000491064999550872 }, "communicator.exchange": { "total": 0.04774355400013519, "count": 1, "is_parallel": true, "self": 0.04774355400013519 }, "steps_from_proto": { "total": 0.0018162510000365728, "count": 1, "is_parallel": true, "self": 0.0004251029999977618, "children": { "_process_rank_one_or_two_observation": { "total": 0.001391148000038811, "count": 8, "is_parallel": true, "self": 0.001391148000038811 } } } } } } }, "UnityEnvironment.step": { "total": 1198.8655441880128, "count": 63248, "is_parallel": true, "self": 31.088556357982725, "children": { "UnityEnvironment._generate_step_input": { "total": 23.24245678001398, "count": 63248, "is_parallel": true, "self": 23.24245678001398 }, "communicator.exchange": { "total": 1048.6214602860473, "count": 63248, "is_parallel": true, "self": 1048.6214602860473 }, "steps_from_proto": { "total": 95.91307076396879, "count": 63248, "is_parallel": true, "self": 18.968272970049384, "children": { "_process_rank_one_or_two_observation": { "total": 76.9447977939194, "count": 505984, "is_parallel": true, "self": 76.9447977939194 } } } } } } } } } } }, "trainer_advance": { "total": 683.573838470008, "count": 63249, "self": 2.452510548995633, "children": { "process_trajectory": { "total": 126.88605736101363, "count": 63249, "self": 126.57637422701373, "children": { "RLTrainer._checkpoint": { "total": 0.3096831339998971, "count": 2, "self": 0.3096831339998971 } } }, "_update_policy": { "total": 554.2352705599988, "count": 444, "self": 306.90653781193305, "children": { "TorchPPOOptimizer.update": { "total": 247.3287327480657, "count": 22833, "self": 247.3287327480657 } } } } } } }, "trainer_threads": { "total": 1.0950006981147453e-06, "count": 1, "self": 1.0950006981147453e-06 }, "TrainerController._save_models": { "total": 0.12860013299996353, "count": 1, "self": 0.0018429689998811227, "children": { "RLTrainer._checkpoint": { "total": 0.1267571640000824, "count": 1, "self": 0.1267571640000824 } } } } } } }