{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2827010452747345, "min": 0.27878057956695557, "max": 1.3358147144317627, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8467.4619140625, "min": 8343.6533203125, "max": 40523.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29872.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29872.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5949585437774658, "min": -0.11364227533340454, "max": 0.654905378818512, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 166.58839416503906, "min": -26.93321990966797, "max": 185.33822631835938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01225257944315672, "min": 0.004778169095516205, "max": 0.5398792624473572, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.430722236633301, "min": 1.275771141052246, "max": 127.95138549804688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06832349438419831, "min": 0.06525146078310369, "max": 0.07581017602517803, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9565289213787764, "min": 0.5649015058286646, "max": 1.071090160831398, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0168747355104036, "min": 0.00016267441986968968, "max": 0.0168747355104036, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2362462971456504, "min": 0.0022774418781756557, "max": 0.2362462971456504, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.542718914364286e-06, "min": 7.542718914364286e-06, "max": 0.00029522070159310003, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010559806480109999, "min": 0.00010559806480109999, "max": 0.0035070146309952, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251420714285715, "min": 0.10251420714285715, "max": 0.19840690000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351989, "min": 1.4351989, "max": 2.5690048000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002611692935714286, "min": 0.0002611692935714286, "max": 0.00984084931, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036563701100000004, "min": 0.0036563701100000004, "max": 0.11692357952000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.024067768827080727, "min": 0.0221833698451519, "max": 0.6140232682228088, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3369487524032593, "min": 0.310567170381546, "max": 4.912186145782471, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.9139784946237, "min": 290.2857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30496.0, "min": 15904.0, "max": 33655.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5659456294353888, "min": -0.9998500519432127, "max": 1.6763687380589545, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.06699790805578, "min": -31.995201662182808, "max": 171.3577987626195, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5659456294353888, "min": -0.9998500519432127, "max": 1.6763687380589545, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.06699790805578, "min": -31.995201662182808, "max": 171.3577987626195, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07804274664933632, "min": 0.07277603369570812, "max": 12.76470751594752, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 7.179932691738941, "min": 5.975544401531806, "max": 204.23532025516033, "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": "1700133366", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 Training2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700135679" }, "total": 2313.347362671, "count": 1, "self": 0.7099156399999629, "children": { "run_training.setup": { "total": 0.06779406800001198, "count": 1, "self": 0.06779406800001198 }, "TrainerController.start_learning": { "total": 2312.5696529630004, "count": 1, "self": 1.437597030977031, "children": { "TrainerController._reset_env": { "total": 4.364818040999808, "count": 1, "self": 4.364818040999808 }, "TrainerController.advance": { "total": 2306.6928190500244, "count": 63917, "self": 1.5091755290027322, "children": { "env_step": { "total": 1653.4276456489952, "count": 63917, "self": 1519.8727314219716, "children": { "SubprocessEnvManager._take_step": { "total": 132.68931758498525, "count": 63917, "self": 4.689221155999576, "children": { "TorchPolicy.evaluate": { "total": 128.00009642898567, "count": 62526, "self": 128.00009642898567 } } }, "workers": { "total": 0.8655966420383265, "count": 63917, "self": 0.0, "children": { "worker_root": { "total": 2307.6589386580154, "count": 63917, "is_parallel": true, "self": 907.56658908803, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025508030000764848, "count": 1, "is_parallel": true, "self": 0.0007278719999703753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018229310001061094, "count": 8, "is_parallel": true, "self": 0.0018229310001061094 } } }, "UnityEnvironment.step": { "total": 0.053754996999941795, "count": 1, "is_parallel": true, "self": 0.000641763999738032, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047979800001485273, "count": 1, "is_parallel": true, "self": 0.00047979800001485273 }, "communicator.exchange": { "total": 0.050888967999981105, "count": 1, "is_parallel": true, "self": 0.050888967999981105 }, "steps_from_proto": { "total": 0.0017444670002078055, "count": 1, "is_parallel": true, "self": 0.0003887240004587511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013557429997490544, "count": 8, "is_parallel": true, "self": 0.0013557429997490544 } } } } } } }, "UnityEnvironment.step": { "total": 1400.0923495699853, "count": 63916, "is_parallel": true, "self": 35.898795952989076, "children": { "UnityEnvironment._generate_step_input": { "total": 24.44069597399516, "count": 63916, "is_parallel": true, "self": 24.44069597399516 }, "communicator.exchange": { "total": 1240.498163851012, "count": 63916, "is_parallel": true, "self": 1240.498163851012 }, "steps_from_proto": { "total": 99.25469379198921, "count": 63916, "is_parallel": true, "self": 19.992510525930584, "children": { "_process_rank_one_or_two_observation": { "total": 79.26218326605863, "count": 511328, "is_parallel": true, "self": 79.26218326605863 } } } } } } } } } } }, "trainer_advance": { "total": 651.7559978720265, "count": 63917, "self": 2.667247995144635, "children": { "process_trajectory": { "total": 124.21948795788194, "count": 63917, "self": 124.06211604788223, "children": { "RLTrainer._checkpoint": { "total": 0.15737190999971062, "count": 2, "self": 0.15737190999971062 } } }, "_update_policy": { "total": 524.8692619189999, "count": 454, "self": 317.4320839739971, "children": { "TorchPPOOptimizer.update": { "total": 207.43717794500276, "count": 22824, "self": 207.43717794500276 } } } } } } }, "trainer_threads": { "total": 1.047999830916524e-06, "count": 1, "self": 1.047999830916524e-06 }, "TrainerController._save_models": { "total": 0.07441779299961127, "count": 1, "self": 0.0013956919997326622, "children": { "RLTrainer._checkpoint": { "total": 0.0730221009998786, "count": 1, "self": 0.0730221009998786 } } } } } } }