{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.364847332239151, "min": 0.364847332239151, "max": 1.4937645196914673, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10992.1201171875, "min": 10992.1201171875, "max": 45314.83984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4493965804576874, "min": -0.11554408073425293, "max": 0.45616114139556885, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 120.88768005371094, "min": -27.730579376220703, "max": 121.3388671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015761176124215126, "min": 0.003372310195118189, "max": 0.22920021414756775, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.2397565841674805, "min": 0.8768006563186646, "max": 55.008052825927734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06590740933394092, "min": 0.06590370954952204, "max": 0.07401375408378608, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9227037306751729, "min": 0.506988610674215, "max": 1.0972383213098225, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012725444129172186, "min": 0.0004586589796410946, "max": 0.014471292679012374, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1781562178084106, "min": 0.006421225714975325, "max": 0.20259809750617325, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.724090282478568e-06, "min": 7.724090282478568e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010813726395469996, "min": 0.00010813726395469996, "max": 0.0035077703307433, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257466428571431, "min": 0.10257466428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360453000000004, "min": 1.3886848, "max": 2.5692566999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026720896214285715, "min": 0.00026720896214285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00374092547, "min": 0.00374092547, "max": 0.11694874433, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01137875858694315, "min": 0.011367379687726498, "max": 0.28142645955085754, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15930262207984924, "min": 0.15914331376552582, "max": 1.9699852466583252, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.26666666666665, "min": 404.26666666666665, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30320.0, "min": 15984.0, "max": 32939.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4356719760100047, "min": -1.0000000521540642, "max": 1.4825405165351726, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.67539820075035, "min": -29.99400170892477, "max": 109.70799822360277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4356719760100047, "min": -1.0000000521540642, "max": 1.4825405165351726, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.67539820075035, "min": -29.99400170892477, "max": 109.70799822360277, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047771389776219926, "min": 0.04771804336092568, "max": 5.385920062661171, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5828542332164943, "min": 3.3402630352647975, "max": 86.17472100257874, "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": "1701853699", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701855891" }, "total": 2191.969353092, "count": 1, "self": 1.257284916000117, "children": { "run_training.setup": { "total": 0.08298645600001464, "count": 1, "self": 0.08298645600001464 }, "TrainerController.start_learning": { "total": 2190.6290817199997, "count": 1, "self": 1.2368424399687683, "children": { "TrainerController._reset_env": { "total": 4.181706311000028, "count": 1, "self": 4.181706311000028 }, "TrainerController.advance": { "total": 2185.094186473031, "count": 63585, "self": 1.398313832050917, "children": { "env_step": { "total": 1543.7241479919717, "count": 63585, "self": 1415.2882457219346, "children": { "SubprocessEnvManager._take_step": { "total": 127.63906251697853, "count": 63585, "self": 4.559394220990725, "children": { "TorchPolicy.evaluate": { "total": 123.0796682959878, "count": 62560, "self": 123.0796682959878 } } }, "workers": { "total": 0.7968397530586344, "count": 63585, "self": 0.0, "children": { "worker_root": { "total": 2186.160820860965, "count": 63585, "is_parallel": true, "self": 885.3358644949476, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0062029270000039105, "count": 1, "is_parallel": true, "self": 0.004292383000006339, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019105439999975715, "count": 8, "is_parallel": true, "self": 0.0019105439999975715 } } }, "UnityEnvironment.step": { "total": 0.04708306200001289, "count": 1, "is_parallel": true, "self": 0.0005940000000350665, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004646649999813235, "count": 1, "is_parallel": true, "self": 0.0004646649999813235 }, "communicator.exchange": { "total": 0.04431207400000403, "count": 1, "is_parallel": true, "self": 0.04431207400000403 }, "steps_from_proto": { "total": 0.001712322999992466, "count": 1, "is_parallel": true, "self": 0.00038718299998663497, "children": { "_process_rank_one_or_two_observation": { "total": 0.001325140000005831, "count": 8, "is_parallel": true, "self": 0.001325140000005831 } } } } } } }, "UnityEnvironment.step": { "total": 1300.8249563660174, "count": 63584, "is_parallel": true, "self": 34.19127417602385, "children": { "UnityEnvironment._generate_step_input": { "total": 23.640750736016116, "count": 63584, "is_parallel": true, "self": 23.640750736016116 }, "communicator.exchange": { "total": 1147.0067821330108, "count": 63584, "is_parallel": true, "self": 1147.0067821330108 }, "steps_from_proto": { "total": 95.98614932096655, "count": 63584, "is_parallel": true, "self": 18.69318082501286, "children": { "_process_rank_one_or_two_observation": { "total": 77.29296849595369, "count": 508672, "is_parallel": true, "self": 77.29296849595369 } } } } } } } } } } }, "trainer_advance": { "total": 639.9717246490084, "count": 63585, "self": 2.464773510980649, "children": { "process_trajectory": { "total": 126.13340320002857, "count": 63585, "self": 125.88988543502859, "children": { "RLTrainer._checkpoint": { "total": 0.24351776499997868, "count": 2, "self": 0.24351776499997868 } } }, "_update_policy": { "total": 511.3735479379992, "count": 451, "self": 305.81021809699007, "children": { "TorchPPOOptimizer.update": { "total": 205.56332984100914, "count": 22767, "self": 205.56332984100914 } } } } } } }, "trainer_threads": { "total": 1.1409997568989638e-06, "count": 1, "self": 1.1409997568989638e-06 }, "TrainerController._save_models": { "total": 0.11634535499979393, "count": 1, "self": 0.0017506539998066728, "children": { "RLTrainer._checkpoint": { "total": 0.11459470099998725, "count": 1, "self": 0.11459470099998725 } } } } } } }