{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4606909155845642, "min": 0.43714478611946106, "max": 1.3890351057052612, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13798.6142578125, "min": 12981.451171875, "max": 42137.76953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4690605700016022, "min": -0.11727041006088257, "max": 0.4980018138885498, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.17729187011719, "min": -28.262168884277344, "max": 135.95449829101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014398873783648014, "min": -0.006284828297793865, "max": 0.4995509088039398, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.8732969760894775, "min": -1.7157580852508545, "max": 118.39356231689453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0712941121762722, "min": 0.0655800352868114, "max": 0.07387820006300679, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.069411682644083, "min": 0.4838501576275027, "max": 1.069411682644083, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015411954958755008, "min": 0.000288538282866579, "max": 0.015411954958755008, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23117932438132513, "min": 0.003173921111532369, "max": 0.23117932438132513, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.573057475680003e-06, "min": 7.573057475680003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011359586213520004, "min": 0.00011359586213520004, "max": 0.003137091254303, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252432000000004, "min": 0.10252432000000004, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378648000000006, "min": 1.3886848, "max": 2.401435, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002621795680000001, "min": 0.0002621795680000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039326935200000015, "min": 0.0039326935200000015, "max": 0.1045951303, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010643676854670048, "min": 0.010643676854670048, "max": 0.5520880818367004, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1596551537513733, "min": 0.15644726157188416, "max": 3.864616632461548, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 372.1875, "min": 352.04938271604937, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29775.0, "min": 15984.0, "max": 32962.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5265265623979931, "min": -1.0000000521540642, "max": 1.5985431862466128, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.59559842944145, "min": -31.998401656746864, "max": 129.48199808597565, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5265265623979931, "min": -1.0000000521540642, "max": 1.5985431862466128, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.59559842944145, "min": -31.998401656746864, "max": 129.48199808597565, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040932992914038756, "min": 0.040932992914038756, "max": 12.415960829705, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.233706440209062, "min": 3.233706440209062, "max": 198.65537327528, "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": "1703601342", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703603487" }, "total": 2145.310186941, "count": 1, "self": 0.4764474190005785, "children": { "run_training.setup": { "total": 0.07238672099992982, "count": 1, "self": 0.07238672099992982 }, "TrainerController.start_learning": { "total": 2144.7613528009997, "count": 1, "self": 1.2716352280117462, "children": { "TrainerController._reset_env": { "total": 2.2448563319999266, "count": 1, "self": 2.2448563319999266 }, "TrainerController.advance": { "total": 2141.1640665119885, "count": 63626, "self": 1.3900983371318034, "children": { "env_step": { "total": 1524.6544232209749, "count": 63626, "self": 1397.6830240319946, "children": { "SubprocessEnvManager._take_step": { "total": 126.147081246987, "count": 63626, "self": 4.555509202920803, "children": { "TorchPolicy.evaluate": { "total": 121.5915720440662, "count": 62558, "self": 121.5915720440662 } } }, "workers": { "total": 0.8243179419932858, "count": 63626, "self": 0.0, "children": { "worker_root": { "total": 2139.8374637500406, "count": 63626, "is_parallel": true, "self": 858.5519115900561, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016692220001459646, "count": 1, "is_parallel": true, "self": 0.0005258419996607699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011433800004851946, "count": 8, "is_parallel": true, "self": 0.0011433800004851946 } } }, "UnityEnvironment.step": { "total": 0.04900357199994687, "count": 1, "is_parallel": true, "self": 0.0005782889998044993, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005131570001140062, "count": 1, "is_parallel": true, "self": 0.0005131570001140062 }, "communicator.exchange": { "total": 0.046311034000154905, "count": 1, "is_parallel": true, "self": 0.046311034000154905 }, "steps_from_proto": { "total": 0.0016010919998734607, "count": 1, "is_parallel": true, "self": 0.00034431200083417934, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012567799990392814, "count": 8, "is_parallel": true, "self": 0.0012567799990392814 } } } } } } }, "UnityEnvironment.step": { "total": 1281.2855521599845, "count": 63625, "is_parallel": true, "self": 34.264528917010466, "children": { "UnityEnvironment._generate_step_input": { "total": 24.14103483302506, "count": 63625, "is_parallel": true, "self": 24.14103483302506 }, "communicator.exchange": { "total": 1124.4779347919575, "count": 63625, "is_parallel": true, "self": 1124.4779347919575 }, "steps_from_proto": { "total": 98.40205361799144, "count": 63625, "is_parallel": true, "self": 19.655919320888188, "children": { "_process_rank_one_or_two_observation": { "total": 78.74613429710325, "count": 509000, "is_parallel": true, "self": 78.74613429710325 } } } } } } } } } } }, "trainer_advance": { "total": 615.1195449538818, "count": 63626, "self": 2.5070267587857415, "children": { "process_trajectory": { "total": 123.97319268609726, "count": 63626, "self": 123.78747826509743, "children": { "RLTrainer._checkpoint": { "total": 0.1857144209998296, "count": 2, "self": 0.1857144209998296 } } }, "_update_policy": { "total": 488.6393255089988, "count": 443, "self": 287.8816277979399, "children": { "TorchPPOOptimizer.update": { "total": 200.75769771105888, "count": 22863, "self": 200.75769771105888 } } } } } } }, "trainer_threads": { "total": 8.970000635599717e-07, "count": 1, "self": 8.970000635599717e-07 }, "TrainerController._save_models": { "total": 0.08079383199947188, "count": 1, "self": 0.001319702999353467, "children": { "RLTrainer._checkpoint": { "total": 0.07947412900011841, "count": 1, "self": 0.07947412900011841 } } } } } } }