{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1332024335861206, "min": 0.1332024335861206, "max": 1.4856574535369873, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3985.4169921875, "min": 3985.4169921875, "max": 45068.90625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999981.0, "min": 29952.0, "max": 2999981.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999981.0, "min": 29952.0, "max": 2999981.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7220757007598877, "min": -0.18479059636592865, "max": 0.9035793542861938, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 210.1240234375, "min": -43.795372009277344, "max": 285.53106689453125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005038607399910688, "min": -0.012448417954146862, "max": 0.3230520784854889, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.466234803199768, "min": -3.6100411415100098, "max": 76.56333923339844, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07077729515054691, "min": 0.06282116506757093, "max": 0.07498741661551488, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9908821321076569, "min": 0.4894676464984472, "max": 1.1248112492327231, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014930455326384746, "min": 0.0009972557743577045, "max": 0.017073321399428614, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20902637456938644, "min": 0.010591151483697167, "max": 0.23902649959200062, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5648137641428542e-06, "min": 1.5648137641428542e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1907392697999958e-05, "min": 2.1907392697999958e-05, "max": 0.0038439619186794, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052157142857143, "min": 0.10052157142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.407302, "min": 1.3897045333333333, "max": 2.7674998000000004, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.210498571428561e-05, "min": 6.210498571428561e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008694697999999986, "min": 0.0008694697999999986, "max": 0.12814392794, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007337778341025114, "min": 0.007315483875572681, "max": 0.38245826959609985, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10272889584302902, "min": 0.10241677612066269, "max": 2.6772079467773438, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 259.08620689655174, "min": 194.99346405228758, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30054.0, "min": 15984.0, "max": 34058.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.637427573381313, "min": -1.0000000521540642, "max": 1.8042763058880442, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 189.9415985122323, "min": -32.000001668930054, "max": 274.2499984949827, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.637427573381313, "min": -1.0000000521540642, "max": 1.8042763058880442, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 189.9415985122323, "min": -32.000001668930054, "max": 274.2499984949827, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0198721539443419, "min": 0.016495678749478875, "max": 6.906697786413133, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3051698575436603, "min": 2.1919405297594494, "max": 110.50716458261013, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690758194", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "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": "1690765988" }, "total": 7794.230711343, "count": 1, "self": 0.4759737079994011, "children": { "run_training.setup": { "total": 0.031696439999905124, "count": 1, "self": 0.031696439999905124 }, "TrainerController.start_learning": { "total": 7793.723041195, "count": 1, "self": 4.897863862055601, "children": { "TrainerController._reset_env": { "total": 4.0931296399999155, "count": 1, "self": 4.0931296399999155 }, "TrainerController.advance": { "total": 7784.6364301319445, "count": 195274, "self": 4.7098956002882915, "children": { "env_step": { "total": 5780.250303420536, "count": 195274, "self": 5419.6898817882, "children": { "SubprocessEnvManager._take_step": { "total": 357.6788286472911, "count": 195274, "self": 15.610241151233367, "children": { "TorchPolicy.evaluate": { "total": 342.0685874960577, "count": 187562, "self": 342.0685874960577 } } }, "workers": { "total": 2.8815929850443354, "count": 195274, "self": 0.0, "children": { "worker_root": { "total": 7775.595906087045, "count": 195274, "is_parallel": true, "self": 2743.7423819867836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002954610000415414, "count": 1, "is_parallel": true, "self": 0.0009622559996387281, "children": { "_process_rank_one_or_two_observation": { "total": 0.001992354000776686, "count": 8, "is_parallel": true, "self": 0.001992354000776686 } } }, "UnityEnvironment.step": { "total": 0.07078826699989804, "count": 1, "is_parallel": true, "self": 0.0005699690000255941, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048718600010033697, "count": 1, "is_parallel": true, "self": 0.00048718600010033697 }, "communicator.exchange": { "total": 0.06776107899986528, "count": 1, "is_parallel": true, "self": 0.06776107899986528 }, "steps_from_proto": { "total": 0.0019700329999068344, "count": 1, "is_parallel": true, "self": 0.0003818060004050494, "children": { "_process_rank_one_or_two_observation": { "total": 0.001588226999501785, "count": 8, "is_parallel": true, "self": 0.001588226999501785 } } } } } } }, "UnityEnvironment.step": { "total": 5031.853524100261, "count": 195273, "is_parallel": true, "self": 108.80878000604389, "children": { "UnityEnvironment._generate_step_input": { "total": 74.82100095282249, "count": 195273, "is_parallel": true, "self": 74.82100095282249 }, "communicator.exchange": { "total": 4510.992968977015, "count": 195273, "is_parallel": true, "self": 4510.992968977015 }, "steps_from_proto": { "total": 337.2307741643799, "count": 195273, "is_parallel": true, "self": 70.52579006369524, "children": { "_process_rank_one_or_two_observation": { "total": 266.70498410068467, "count": 1562184, "is_parallel": true, "self": 266.70498410068467 } } } } } } } } } } }, "trainer_advance": { "total": 1999.6762311111206, "count": 195274, "self": 8.923560649340743, "children": { "process_trajectory": { "total": 365.5521225788193, "count": 195274, "self": 364.8516358988195, "children": { "RLTrainer._checkpoint": { "total": 0.7004866799998126, "count": 6, "self": 0.7004866799998126 } } }, "_update_policy": { "total": 1625.2005478829606, "count": 1395, "self": 1055.4422268171388, "children": { "TorchPPOOptimizer.update": { "total": 569.7583210658217, "count": 68433, "self": 569.7583210658217 } } } } } } }, "trainer_threads": { "total": 8.990009519038722e-07, "count": 1, "self": 8.990009519038722e-07 }, "TrainerController._save_models": { "total": 0.09561666199988395, "count": 1, "self": 0.0014602150004066061, "children": { "RLTrainer._checkpoint": { "total": 0.09415644699947734, "count": 1, "self": 0.09415644699947734 } } } } } } }