{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32639774680137634, "min": 0.30519115924835205, "max": 1.3938130140304565, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9739.708984375, "min": 9058.0732421875, "max": 42282.7109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5136400461196899, "min": -0.15697559714317322, "max": 0.5169239044189453, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.73736572265625, "min": -37.203216552734375, "max": 142.15406799316406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010383383370935917, "min": 0.0004272554360795766, "max": 0.4326534867286682, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.8450469970703125, "min": 0.1102319061756134, "max": 102.53887939453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06840240258123921, "min": 0.06398481042952202, "max": 0.07415285551495589, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.026036038718588, "min": 0.5190699886046912, "max": 1.0895167985290755, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012932747404480633, "min": 0.0010952744237192873, "max": 0.015198745485676447, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19399121106720948, "min": 0.013467060477605675, "max": 0.21278243679947026, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.512377495906661e-06, "min": 7.512377495906661e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011268566243859991, "min": 0.00011268566243859991, "max": 0.0035078780307073996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250409333333331, "min": 0.10250409333333331, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375613999999997, "min": 1.3886848, "max": 2.5692926000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026015892399999986, "min": 0.00026015892399999986, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039023838599999976, "min": 0.0039023838599999976, "max": 0.11695233074, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008507356978952885, "min": 0.008323481306433678, "max": 0.6334707140922546, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12761035561561584, "min": 0.11652873456478119, "max": 4.434295177459717, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 391.50602409638554, "min": 332.3837209302326, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32495.0, "min": 15984.0, "max": 33585.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4939243725341995, "min": -1.0000000521540642, "max": 1.6210999856161517, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.50179854780436, "min": -29.324001654982567, "max": 139.41459876298904, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4939243725341995, "min": -1.0000000521540642, "max": 1.6210999856161517, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.50179854780436, "min": -29.324001654982567, "max": 139.41459876298904, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033710069716063315, "min": 0.029897214158429348, "max": 12.29168987646699, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.764225716717192, "min": 2.4811825732904254, "max": 196.66703802347183, "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": "1694045140", "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]", "command_line_arguments": "/home/cogstack/.local/share/virtualenvs/optuna-kV9yCCBS/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1694049261" }, "total": 4120.660248577013, "count": 1, "self": 1.6426992401247844, "children": { "run_training.setup": { "total": 0.02219328796491027, "count": 1, "self": 0.02219328796491027 }, "TrainerController.start_learning": { "total": 4118.995356048923, "count": 1, "self": 2.1875440881121904, "children": { "TrainerController._reset_env": { "total": 5.1148424099665135, "count": 1, "self": 5.1148424099665135 }, "TrainerController.advance": { "total": 4111.490642395918, "count": 63906, "self": 2.1899623499484733, "children": { "env_step": { "total": 2453.076377776335, "count": 63906, "self": 1915.5717223570682, "children": { "SubprocessEnvManager._take_step": { "total": 536.161655363976, "count": 63906, "self": 8.45604878431186, "children": { "TorchPolicy.evaluate": { "total": 527.7056065796642, "count": 62559, "self": 527.7056065796642 } } }, "workers": { "total": 1.3430000552907586, "count": 63906, "self": 0.0, "children": { "worker_root": { "total": 4114.536010715412, "count": 63906, "is_parallel": true, "self": 2372.4226331268437, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002617312013171613, "count": 1, "is_parallel": true, "self": 0.0006507928483188152, "children": { "_process_rank_one_or_two_observation": { "total": 0.001966519164852798, "count": 8, "is_parallel": true, "self": 0.001966519164852798 } } }, "UnityEnvironment.step": { "total": 0.04317775694653392, "count": 1, "is_parallel": true, "self": 0.00047633692156523466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.001061632065102458, "count": 1, "is_parallel": true, "self": 0.001061632065102458 }, "communicator.exchange": { "total": 0.040213312953710556, "count": 1, "is_parallel": true, "self": 0.040213312953710556 }, "steps_from_proto": { "total": 0.0014264750061556697, "count": 1, "is_parallel": true, "self": 0.00038572808261960745, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010407469235360622, "count": 8, "is_parallel": true, "self": 0.0010407469235360622 } } } } } } }, "UnityEnvironment.step": { "total": 1742.1133775885683, "count": 63905, "is_parallel": true, "self": 39.28874889528379, "children": { "UnityEnvironment._generate_step_input": { "total": 25.8800827373052, "count": 63905, "is_parallel": true, "self": 25.8800827373052 }, "communicator.exchange": { "total": 1556.2213466416579, "count": 63905, "is_parallel": true, "self": 1556.2213466416579 }, "steps_from_proto": { "total": 120.72319931432139, "count": 63905, "is_parallel": true, "self": 25.25668095133733, "children": { "_process_rank_one_or_two_observation": { "total": 95.46651836298406, "count": 511240, "is_parallel": true, "self": 95.46651836298406 } } } } } } } } } } }, "trainer_advance": { "total": 1656.2243022696348, "count": 63906, "self": 4.390958571573719, "children": { "process_trajectory": { "total": 298.22997528105043, "count": 63906, "self": 297.6076368311187, "children": { "RLTrainer._checkpoint": { "total": 0.6223384499317035, "count": 2, "self": 0.6223384499317035 } } }, "_update_policy": { "total": 1353.6033684170106, "count": 456, "self": 750.6762299688999, "children": { "TorchPPOOptimizer.update": { "total": 602.9271384481108, "count": 22803, "self": 602.9271384481108 } } } } } } }, "trainer_threads": { "total": 1.6569392755627632e-06, "count": 1, "self": 1.6569392755627632e-06 }, "TrainerController._save_models": { "total": 0.20232549798674881, "count": 1, "self": 0.0026690280064940453, "children": { "RLTrainer._checkpoint": { "total": 0.19965646998025477, "count": 1, "self": 0.19965646998025477 } } } } } } }