{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3111456334590912, "min": 0.3111456334590912, "max": 1.5009832382202148, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9219.8671875, "min": 9219.8671875, "max": 45533.828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7260782122612, "min": -0.07720991224050522, "max": 0.7344732880592346, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 217.09738159179688, "min": -18.684799194335938, "max": 217.09738159179688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.029486682265996933, "min": -0.029486682265996933, "max": 0.4009776711463928, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.81651782989502, "min": -8.81651782989502, "max": 95.03170776367188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07179472637445931, "min": 0.06450787445809757, "max": 0.07269155095162293, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0051261692424305, "min": 0.505883368833764, "max": 1.0648508537560701, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017251064403570212, "min": 0.0014038747493114597, "max": 0.017448911799976524, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.241514901649983, "min": 0.019654246490360437, "max": 0.24428476519967135, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6184688891142835e-06, "min": 7.6184688891142835e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010665856444759997, "min": 0.00010665856444759997, "max": 0.0036344287885238, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253945714285714, "min": 0.10253945714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355524, "min": 1.3886848, "max": 2.6176234000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026369176857142854, "min": 0.00026369176857142854, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036916847599999998, "min": 0.0036916847599999998, "max": 0.12116647237999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010530875995755196, "min": 0.010530875995755196, "max": 0.33315134048461914, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14743226766586304, "min": 0.14743226766586304, "max": 2.332059383392334, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 253.65833333333333, "min": 253.65833333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30439.0, "min": 15984.0, "max": 33824.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7296683156241974, "min": -1.0000000521540642, "max": 1.7296683156241974, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 207.56019787490368, "min": -27.627601698040962, "max": 207.56019787490368, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7296683156241974, "min": -1.0000000521540642, "max": 1.7296683156241974, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 207.56019787490368, "min": -27.627601698040962, "max": 207.56019787490368, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02786530505315265, "min": 0.02786530505315265, "max": 6.262187298387289, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.343836606378318, "min": 3.1211297542904504, "max": 100.19499677419662, "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": "1709199300", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/uoch/tf/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1709200320" }, "total": 1019.6177796029997, "count": 1, "self": 0.2199475249999523, "children": { "run_training.setup": { "total": 0.017644823999944492, "count": 1, "self": 0.017644823999944492 }, "TrainerController.start_learning": { "total": 1019.3801872539998, "count": 1, "self": 1.1459509159431036, "children": { "TrainerController._reset_env": { "total": 1.2272712379999575, "count": 1, "self": 1.2272712379999575 }, "TrainerController.advance": { "total": 1016.9594244020573, "count": 64294, "self": 1.0191114259205278, "children": { "env_step": { "total": 633.1819835521319, "count": 64294, "self": 545.8175882292626, "children": { "SubprocessEnvManager._take_step": { "total": 86.6475909638948, "count": 64294, "self": 3.139405604843887, "children": { "TorchPolicy.evaluate": { "total": 83.50818535905091, "count": 62558, "self": 83.50818535905091 } } }, "workers": { "total": 0.7168043589745139, "count": 64294, "self": 0.0, "children": { "worker_root": { "total": 1018.0212203629553, "count": 64294, "is_parallel": true, "self": 537.0865103168999, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011268339994785492, "count": 1, "is_parallel": true, "self": 0.00033690600048430497, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007899279989942443, "count": 8, "is_parallel": true, "self": 0.0007899279989942443 } } }, "UnityEnvironment.step": { "total": 0.023086023999894678, "count": 1, "is_parallel": true, "self": 0.0002169680010410957, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019685799998114817, "count": 1, "is_parallel": true, "self": 0.00019685799998114817 }, "communicator.exchange": { "total": 0.02202162999947177, "count": 1, "is_parallel": true, "self": 0.02202162999947177 }, "steps_from_proto": { "total": 0.0006505679994006641, "count": 1, "is_parallel": true, "self": 0.0001567819999763742, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004937859994242899, "count": 8, "is_parallel": true, "self": 0.0004937859994242899 } } } } } } }, "UnityEnvironment.step": { "total": 480.93471004605544, "count": 64293, "is_parallel": true, "self": 12.848695010178744, "children": { "UnityEnvironment._generate_step_input": { "total": 9.265842332049942, "count": 64293, "is_parallel": true, "self": 9.265842332049942 }, "communicator.exchange": { "total": 421.26430687983066, "count": 64293, "is_parallel": true, "self": 421.26430687983066 }, "steps_from_proto": { "total": 37.5558658239961, "count": 64293, "is_parallel": true, "self": 8.493090158099221, "children": { "_process_rank_one_or_two_observation": { "total": 29.06277566589688, "count": 514344, "is_parallel": true, "self": 29.06277566589688 } } } } } } } } } } }, "trainer_advance": { "total": 382.75832942400484, "count": 64294, "self": 2.103287345937133, "children": { "process_trajectory": { "total": 69.66206762006914, "count": 64294, "self": 69.53056664706946, "children": { "RLTrainer._checkpoint": { "total": 0.13150097299967456, "count": 2, "self": 0.13150097299967456 } } }, "_update_policy": { "total": 310.99297445799857, "count": 457, "self": 196.21456751203823, "children": { "TorchPPOOptimizer.update": { "total": 114.77840694596034, "count": 22791, "self": 114.77840694596034 } } } } } } }, "trainer_threads": { "total": 5.399997462518513e-07, "count": 1, "self": 5.399997462518513e-07 }, "TrainerController._save_models": { "total": 0.04754015799971967, "count": 1, "self": 0.0009103779993893113, "children": { "RLTrainer._checkpoint": { "total": 0.046629780000330356, "count": 1, "self": 0.046629780000330356 } } } } } } }