{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1899246871471405, "min": 0.17638619244098663, "max": 1.5071728229522705, "count": 71 }, "Pyramids.Policy.Entropy.sum": { "value": 5761.55517578125, "min": 5308.51904296875, "max": 45721.59375, "count": 71 }, "Pyramids.Step.mean": { "value": 2129988.0, "min": 29952.0, "max": 2129988.0, "count": 71 }, "Pyramids.Step.sum": { "value": 2129988.0, "min": 29952.0, "max": 2129988.0, "count": 71 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6611337065696716, "min": -0.14305652678012848, "max": 0.831444501876831, "count": 71 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 188.42311096191406, "min": -33.904396057128906, "max": 246.93902587890625, "count": 71 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010597058571875095, "min": -0.009730725549161434, "max": 0.4610251188278198, "count": 71 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0201616287231445, "min": -2.568911552429199, "max": 109.26295471191406, "count": 71 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.068356475822622, "min": 0.06495938123926338, "max": 0.07362873828969896, "count": 71 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.956990661516708, "min": 0.49700992545594685, "max": 1.057489817682996, "count": 71 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016046083228069448, "min": 3.6737994545330406e-05, "max": 0.017089099375187374, "count": 71 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22464516519297226, "min": 0.0004775939290892953, "max": 0.24165279815582946, "count": 71 }, "Pyramids.Policy.LearningRate.mean": { "value": 8.844184194798095e-05, "min": 8.844184194798095e-05, "max": 0.00029838354339596195, "count": 71 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0012381857872717334, "min": 0.0012381857872717334, "max": 0.003969017676994133, "count": 71 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1294805904761905, "min": 0.1294805904761905, "max": 0.19946118095238097, "count": 71 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.812728266666667, "min": 1.3962282666666668, "max": 2.723005866666666, "count": 71 }, "Pyramids.Policy.Beta.mean": { "value": 0.0029551109885714287, "min": 0.0029551109885714287, "max": 0.009946171977142856, "count": 71 }, "Pyramids.Policy.Beta.sum": { "value": 0.04137155384, "min": 0.04137155384, "max": 0.13230828608, "count": 71 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0061418721452355385, "min": 0.006137923803180456, "max": 0.4193947911262512, "count": 71 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08598621189594269, "min": 0.08593093603849411, "max": 2.9357635974884033, "count": 71 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 290.57522123893807, "min": 236.6341463414634, "max": 999.0, "count": 71 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32835.0, "min": 15984.0, "max": 33393.0, "count": 71 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6183035565939332, "min": -1.0000000521540642, "max": 1.7623278562162743, "count": 71 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.24999833852053, "min": -31.992401644587517, "max": 215.00399845838547, "count": 71 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6183035565939332, "min": -1.0000000521540642, "max": 1.7623278562162743, "count": 71 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.24999833852053, "min": -31.992401644587517, "max": 215.00399845838547, "count": 71 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01866999736258939, "min": 0.01607513840972082, "max": 9.082109808921814, "count": 71 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0910397046100115, "min": 1.7847861538466532, "max": 145.31375694274902, "count": 71 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 71 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 71 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680285413", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/u/miniconda3/envs/huggingface-unity/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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", "numpy_version": "1.21.2", "end_time_seconds": "1680288277" }, "total": 2864.7832216079996, "count": 1, "self": 10.00369040699934, "children": { "run_training.setup": { "total": 0.007458585000676976, "count": 1, "self": 0.007458585000676976 }, "TrainerController.start_learning": { "total": 2854.7720726159996, "count": 1, "self": 1.6636979613031144, "children": { "TrainerController._reset_env": { "total": 2.484166225000081, "count": 1, "self": 2.484166225000081 }, "TrainerController.advance": { "total": 2850.5487606066954, "count": 138485, "self": 1.4875498086448715, "children": { "env_step": { "total": 1688.3825712442394, "count": 138485, "self": 1347.567573402992, "children": { "SubprocessEnvManager._take_step": { "total": 339.8171543052031, "count": 138485, "self": 4.912403645152153, "children": { "TorchPolicy.evaluate": { "total": 334.9047506600509, "count": 134473, "self": 334.9047506600509 } } }, "workers": { "total": 0.9978435360444564, "count": 138484, "self": 0.0, "children": { "worker_root": { "total": 2850.5088440389536, "count": 138484, "is_parallel": true, "self": 1606.8530033502811, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008661690008011647, "count": 1, "is_parallel": true, "self": 0.00026113700005225837, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006050320007489063, "count": 8, "is_parallel": true, "self": 0.0006050320007489063 } } }, "UnityEnvironment.step": { "total": 0.02002324499972019, "count": 1, "is_parallel": true, "self": 0.00017584800025360892, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016947800031630322, "count": 1, "is_parallel": true, "self": 0.00016947800031630322 }, "communicator.exchange": { "total": 0.019133155999952578, "count": 1, "is_parallel": true, "self": 0.019133155999952578 }, "steps_from_proto": { "total": 0.000544762999197701, "count": 1, "is_parallel": true, "self": 0.0001267669995286269, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004179959996690741, "count": 8, "is_parallel": true, "self": 0.0004179959996690741 } } } } } } }, "UnityEnvironment.step": { "total": 1243.6558406886725, "count": 138483, "is_parallel": true, "self": 23.94614459981949, "children": { "UnityEnvironment._generate_step_input": { "total": 15.779218399952697, "count": 138483, "is_parallel": true, "self": 15.779218399952697 }, "communicator.exchange": { "total": 1137.4605200499082, "count": 138483, "is_parallel": true, "self": 1137.4605200499082 }, "steps_from_proto": { "total": 66.46995763899213, "count": 138483, "is_parallel": true, "self": 15.231901963500604, "children": { "_process_rank_one_or_two_observation": { "total": 51.23805567549152, "count": 1107864, "is_parallel": true, "self": 51.23805567549152 } } } } } } } } } } }, "trainer_advance": { "total": 1160.678639553811, "count": 138484, "self": 2.846753787648595, "children": { "process_trajectory": { "total": 193.68280271715867, "count": 138484, "self": 193.42283557715837, "children": { "RLTrainer._checkpoint": { "total": 0.25996714000029897, "count": 4, "self": 0.25996714000029897 } } }, "_update_policy": { "total": 964.1490830490038, "count": 987, "self": 439.4324586299117, "children": { "TorchPPOOptimizer.update": { "total": 524.7166244190921, "count": 49125, "self": 524.7166244190921 } } } } } } }, "trainer_threads": { "total": 5.400015652412549e-07, "count": 1, "self": 5.400015652412549e-07 }, "TrainerController._save_models": { "total": 0.07544728299944836, "count": 1, "self": 0.0013531429976865184, "children": { "RLTrainer._checkpoint": { "total": 0.07409414000176184, "count": 1, "self": 0.07409414000176184 } } } } } } }