{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41527074575424194, "min": 0.41527074575424194, "max": 1.4686696529388428, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12424.900390625, "min": 12424.900390625, "max": 44553.5625, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5986225605010986, "min": -0.14470091462135315, "max": 0.6275726556777954, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 170.607421875, "min": -34.29411697387695, "max": 175.7203369140625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011461108922958374, "min": -0.011850395239889622, "max": 0.3242793381214142, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.266416072845459, "min": -3.318110704421997, "max": 78.15132141113281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06848049495343325, "min": 0.0662977954152988, "max": 0.0750831764767418, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0272074243014988, "min": 0.5007734487258734, "max": 1.028375415422488, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014373475379478702, "min": 0.0001282080601979811, "max": 0.016134823811409574, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21560213069218054, "min": 0.0014102886621777922, "max": 0.24195037320411455, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 8.729540839206669e-06, "min": 8.729540839206669e-06, "max": 0.00034434240161645714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00013094311258810004, "min": 0.00013094311258810004, "max": 0.0036645870529751997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249412666666667, "min": 0.10249412666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374119000000002, "min": 1.3886848, "max": 2.4014147, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002591632540000001, "min": 0.0002591632540000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003887448810000001, "min": 0.003887448810000001, "max": 0.10472777752000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010796514339745045, "min": 0.010636893101036549, "max": 0.43772488832473755, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16194771230220795, "min": 0.14891649782657623, "max": 3.0640742778778076, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 321.65909090909093, "min": 320.7613636363636, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28306.0, "min": 15984.0, "max": 34191.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6328795288096776, "min": -1.0000000521540642, "max": 1.6577124811398487, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 143.69339853525162, "min": -31.998401656746864, "max": 159.14039818942547, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6328795288096776, "min": -1.0000000521540642, "max": 1.6577124811398487, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 143.69339853525162, "min": -31.998401656746864, "max": 159.14039818942547, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03617759909932581, "min": 0.03537809271711012, "max": 9.330483506433666, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1836287207406713, "min": 3.1836287207406713, "max": 149.28773610293865, "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": "1683038935", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683041496" }, "total": 2560.309452869, "count": 1, "self": 0.5382950169996548, "children": { "run_training.setup": { "total": 0.04720359299994925, "count": 1, "self": 0.04720359299994925 }, "TrainerController.start_learning": { "total": 2559.7239542590005, "count": 1, "self": 1.882749658960165, "children": { "TrainerController._reset_env": { "total": 4.638096714999847, "count": 1, "self": 4.638096714999847 }, "TrainerController.advance": { "total": 2553.0921184380404, "count": 63722, "self": 1.8439538590787379, "children": { "env_step": { "total": 1838.0413715179686, "count": 63722, "self": 1700.759900933833, "children": { "SubprocessEnvManager._take_step": { "total": 136.1661480230805, "count": 63722, "self": 5.781753429050923, "children": { "TorchPolicy.evaluate": { "total": 130.38439459402957, "count": 62551, "self": 130.38439459402957 } } }, "workers": { "total": 1.115322561055109, "count": 63722, "self": 0.0, "children": { "worker_root": { "total": 2553.02942234395, "count": 63722, "is_parallel": true, "self": 991.5787320539471, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019035689999782335, "count": 1, "is_parallel": true, "self": 0.0005064549998223811, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013971140001558524, "count": 8, "is_parallel": true, "self": 0.0013971140001558524 } } }, "UnityEnvironment.step": { "total": 0.058730231999788884, "count": 1, "is_parallel": true, "self": 0.0005944239999280398, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005482120000124269, "count": 1, "is_parallel": true, "self": 0.0005482120000124269 }, "communicator.exchange": { "total": 0.055692323999892324, "count": 1, "is_parallel": true, "self": 0.055692323999892324 }, "steps_from_proto": { "total": 0.001895271999956094, "count": 1, "is_parallel": true, "self": 0.00038874599954397127, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015065260004121228, "count": 8, "is_parallel": true, "self": 0.0015065260004121228 } } } } } } }, "UnityEnvironment.step": { "total": 1561.450690290003, "count": 63721, "is_parallel": true, "self": 37.1608397589614, "children": { "UnityEnvironment._generate_step_input": { "total": 25.69688357801988, "count": 63721, "is_parallel": true, "self": 25.69688357801988 }, "communicator.exchange": { "total": 1383.638133103052, "count": 63721, "is_parallel": true, "self": 1383.638133103052 }, "steps_from_proto": { "total": 114.95483384996965, "count": 63721, "is_parallel": true, "self": 24.424521113055334, "children": { "_process_rank_one_or_two_observation": { "total": 90.53031273691431, "count": 509768, "is_parallel": true, "self": 90.53031273691431 } } } } } } } } } } }, "trainer_advance": { "total": 713.206793060993, "count": 63722, "self": 3.2524882970058115, "children": { "process_trajectory": { "total": 120.4493139199908, "count": 63722, "self": 120.22319856399099, "children": { "RLTrainer._checkpoint": { "total": 0.22611535599980925, "count": 2, "self": 0.22611535599980925 } } }, "_update_policy": { "total": 589.5049908439964, "count": 439, "self": 382.1550882140373, "children": { "TorchPPOOptimizer.update": { "total": 207.34990262995916, "count": 22839, "self": 207.34990262995916 } } } } } } }, "trainer_threads": { "total": 1.160000010713702e-06, "count": 1, "self": 1.160000010713702e-06 }, "TrainerController._save_models": { "total": 0.1109882870000547, "count": 1, "self": 0.0017257449999306118, "children": { "RLTrainer._checkpoint": { "total": 0.10926254200012409, "count": 1, "self": 0.10926254200012409 } } } } } } }