{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.359508752822876, "min": 0.34822776913642883, "max": 1.476664423942566, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10750.75, "min": 10413.4033203125, "max": 44796.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36237576603889465, "min": -0.10081224888563156, "max": 0.45428138971328735, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 95.66720581054688, "min": -24.094127655029297, "max": 119.47600555419922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01337360218167305, "min": 0.003808769164606929, "max": 0.2585873305797577, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.5306310653686523, "min": 0.9826624393463135, "max": 61.36722183227539, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06900113667962356, "min": 0.06601375369818135, "max": 0.07342804942987025, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9660159135147297, "min": 0.4973633598433219, "max": 1.063147431249187, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009818019565563274, "min": 0.0011736706208861556, "max": 0.014311311577676816, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13745227391788584, "min": 0.015257718071520023, "max": 0.20035836208747543, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.261233293907138e-06, "min": 7.261233293907138e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010165726611469993, "min": 0.00010165726611469993, "max": 0.0035075933308022994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242037857142858, "min": 0.10242037857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338853, "min": 1.3886848, "max": 2.5691976999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025179581928571417, "min": 0.00025179581928571417, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003525141469999998, "min": 0.003525141469999998, "max": 0.11694285023, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015484215691685677, "min": 0.015484215691685677, "max": 0.459351122379303, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21677902340888977, "min": 0.21677902340888977, "max": 3.2154579162597656, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 502.53333333333336, "min": 426.5492957746479, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30152.0, "min": 15984.0, "max": 32614.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2894203141331673, "min": -1.0000000521540642, "max": 1.504479391829056, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 76.07579853385687, "min": -28.336401626467705, "max": 102.3045986443758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2894203141331673, "min": -1.0000000521540642, "max": 1.504479391829056, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 76.07579853385687, "min": -28.336401626467705, "max": 102.3045986443758, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0810127073521055, "min": 0.07529577830540751, "max": 9.221514103934169, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.779749733774224, "min": 4.7717982804751955, "max": 147.5442256629467, "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": "1727076167", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727079133" }, "total": 2965.7518021469996, "count": 1, "self": 0.6542106919996513, "children": { "run_training.setup": { "total": 0.24344144500014409, "count": 1, "self": 0.24344144500014409 }, "TrainerController.start_learning": { "total": 2964.85415001, "count": 1, "self": 2.3378362889798154, "children": { "TrainerController._reset_env": { "total": 4.025659385999916, "count": 1, "self": 4.025659385999916 }, "TrainerController.advance": { "total": 2958.4080452520216, "count": 63549, "self": 2.48969378302354, "children": { "env_step": { "total": 1964.0672352540034, "count": 63549, "self": 1813.4807992150809, "children": { "SubprocessEnvManager._take_step": { "total": 149.23313975793144, "count": 63549, "self": 6.389285686954736, "children": { "TorchPolicy.evaluate": { "total": 142.8438540709767, "count": 62569, "self": 142.8438540709767 } } }, "workers": { "total": 1.3532962809911169, "count": 63549, "self": 0.0, "children": { "worker_root": { "total": 2958.5943868020545, "count": 63549, "is_parallel": true, "self": 1318.1576680431235, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004540205000012065, "count": 1, "is_parallel": true, "self": 0.001743535000287011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027966699997250544, "count": 8, "is_parallel": true, "self": 0.0027966699997250544 } } }, "UnityEnvironment.step": { "total": 0.0651145980000365, "count": 1, "is_parallel": true, "self": 0.0007845810002891085, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005476929998167179, "count": 1, "is_parallel": true, "self": 0.0005476929998167179 }, "communicator.exchange": { "total": 0.06150889099990309, "count": 1, "is_parallel": true, "self": 0.06150889099990309 }, "steps_from_proto": { "total": 0.0022734330000275804, "count": 1, "is_parallel": true, "self": 0.0004202509996957815, "children": { "_process_rank_one_or_two_observation": { "total": 0.001853182000331799, "count": 8, "is_parallel": true, "self": 0.001853182000331799 } } } } } } }, "UnityEnvironment.step": { "total": 1640.436718758931, "count": 63548, "is_parallel": true, "self": 48.05058888600365, "children": { "UnityEnvironment._generate_step_input": { "total": 28.758519646955847, "count": 63548, "is_parallel": true, "self": 28.758519646955847 }, "communicator.exchange": { "total": 1438.4572441540472, "count": 63548, "is_parallel": true, "self": 1438.4572441540472 }, "steps_from_proto": { "total": 125.17036607192426, "count": 63548, "is_parallel": true, "self": 26.89256624312202, "children": { "_process_rank_one_or_two_observation": { "total": 98.27779982880224, "count": 508384, "is_parallel": true, "self": 98.27779982880224 } } } } } } } } } } }, "trainer_advance": { "total": 991.8511162149946, "count": 63549, "self": 4.383852298964257, "children": { "process_trajectory": { "total": 157.55749755703482, "count": 63549, "self": 157.2563762720356, "children": { "RLTrainer._checkpoint": { "total": 0.3011212849992262, "count": 2, "self": 0.3011212849992262 } } }, "_update_policy": { "total": 829.9097663589955, "count": 451, "self": 345.2641838850393, "children": { "TorchPPOOptimizer.update": { "total": 484.6455824739562, "count": 22743, "self": 484.6455824739562 } } } } } } }, "trainer_threads": { "total": 1.1539996194187552e-06, "count": 1, "self": 1.1539996194187552e-06 }, "TrainerController._save_models": { "total": 0.08260792899909575, "count": 1, "self": 0.0025676249997559353, "children": { "RLTrainer._checkpoint": { "total": 0.08004030399933981, "count": 1, "self": 0.08004030399933981 } } } } } } }