{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.738794207572937, "min": 0.738794207572937, "max": 1.4520542621612549, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22199.2890625, "min": 22199.2890625, "max": 44049.51953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989923.0, "min": 29913.0, "max": 989923.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989923.0, "min": 29913.0, "max": 989923.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3829733729362488, "min": -0.10160267353057861, "max": 0.39602038264274597, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.6368637084961, "min": -24.486244201660156, "max": 104.94540405273438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.08976131677627563, "min": -0.08976131677627563, "max": 0.5205562710762024, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -24.056032180786133, "min": -24.056032180786133, "max": 123.37184143066406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06810544748911161, "min": 0.06468911192264103, "max": 0.07184554738201068, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0215817123366742, "min": 0.6454602630634363, "max": 1.0776832107301602, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014580314401312718, "min": 0.0004623772602906033, "max": 0.014580314401312718, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21870471601969077, "min": 0.006010904383777843, "max": 0.21870471601969077, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.533717488793334e-06, "min": 7.533717488793334e-06, "max": 0.00029478956840347777, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001130057623319, "min": 0.0001130057623319, "max": 0.0036090774969741992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251120666666667, "min": 0.10251120666666667, "max": 0.1982631888888889, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376681, "min": 1.4784678999999996, "max": 2.5695717000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000260869546, "min": 0.000260869546, "max": 0.00982649257, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00391304319, "min": 0.00391304319, "max": 0.12031227742, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007368649821728468, "min": 0.007368649821728468, "max": 0.4125029742717743, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11052975058555603, "min": 0.10342450439929962, "max": 3.712526798248291, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 460.33846153846156, "min": 460.33846153846156, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29922.0, "min": 17607.0, "max": 33196.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3549722760915757, "min": -0.9999500522390008, "max": 1.3931103209997047, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 88.07319794595242, "min": -31.998401671648026, "max": 88.07319794595242, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3549722760915757, "min": -0.9999500522390008, "max": 1.3931103209997047, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 88.07319794595242, "min": -31.998401671648026, "max": 88.07319794595242, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03510226650754563, "min": 0.03510226650754563, "max": 8.346237605644596, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.281647322990466, "min": 2.281647322990466, "max": 150.23227690160275, "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": "1745927096", "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 --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "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": "1745929168" }, "total": 2071.555237027, "count": 1, "self": 0.810721678000391, "children": { "run_training.setup": { "total": 0.020619382999939262, "count": 1, "self": 0.020619382999939262 }, "TrainerController.start_learning": { "total": 2070.723895966, "count": 1, "self": 1.2870804299536758, "children": { "TrainerController._reset_env": { "total": 3.0998348840000745, "count": 1, "self": 3.0998348840000745 }, "TrainerController.advance": { "total": 2066.2112741260466, "count": 63423, "self": 1.3811120400041546, "children": { "env_step": { "total": 1399.9945715180309, "count": 63423, "self": 1250.3491638200849, "children": { "SubprocessEnvManager._take_step": { "total": 148.88243431298247, "count": 63423, "self": 4.457244530048683, "children": { "TorchPolicy.evaluate": { "total": 144.42518978293378, "count": 62551, "self": 144.42518978293378 } } }, "workers": { "total": 0.7629733849635159, "count": 63423, "self": 0.0, "children": { "worker_root": { "total": 2065.7964937230654, "count": 63423, "is_parallel": true, "self": 923.3793409991251, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002423921999934464, "count": 1, "is_parallel": true, "self": 0.0007147649996568362, "children": { "_process_rank_one_or_two_observation": { "total": 0.001709157000277628, "count": 8, "is_parallel": true, "self": 0.001709157000277628 } } }, "UnityEnvironment.step": { "total": 0.05063362700002472, "count": 1, "is_parallel": true, "self": 0.0005287579999730951, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005012480000914366, "count": 1, "is_parallel": true, "self": 0.0005012480000914366 }, "communicator.exchange": { "total": 0.0480475800000022, "count": 1, "is_parallel": true, "self": 0.0480475800000022 }, "steps_from_proto": { "total": 0.001556040999957986, "count": 1, "is_parallel": true, "self": 0.00034479300006751146, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012112479998904746, "count": 8, "is_parallel": true, "self": 0.0012112479998904746 } } } } } } }, "UnityEnvironment.step": { "total": 1142.4171527239403, "count": 63422, "is_parallel": true, "self": 31.18260735005515, "children": { "UnityEnvironment._generate_step_input": { "total": 22.463243120928382, "count": 63422, "is_parallel": true, "self": 22.463243120928382 }, "communicator.exchange": { "total": 995.7341018119748, "count": 63422, "is_parallel": true, "self": 995.7341018119748 }, "steps_from_proto": { "total": 93.0372004409819, "count": 63422, "is_parallel": true, "self": 18.503335067896387, "children": { "_process_rank_one_or_two_observation": { "total": 74.53386537308552, "count": 507376, "is_parallel": true, "self": 74.53386537308552 } } } } } } } } } } }, "trainer_advance": { "total": 664.8355905680116, "count": 63423, "self": 2.5289919580136484, "children": { "process_trajectory": { "total": 123.3249099159998, "count": 63423, "self": 123.09534723499928, "children": { "RLTrainer._checkpoint": { "total": 0.22956268100051602, "count": 2, "self": 0.22956268100051602 } } }, "_update_policy": { "total": 538.9816886939982, "count": 455, "self": 298.0867833819941, "children": { "TorchPPOOptimizer.update": { "total": 240.89490531200408, "count": 22770, "self": 240.89490531200408 } } } } } } }, "trainer_threads": { "total": 1.1889997040270828e-06, "count": 1, "self": 1.1889997040270828e-06 }, "TrainerController._save_models": { "total": 0.12570533699999942, "count": 1, "self": 0.0015936770000735123, "children": { "RLTrainer._checkpoint": { "total": 0.1241116599999259, "count": 1, "self": 0.1241116599999259 } } } } } } }