{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20191000401973724, "min": 0.20191000401973724, "max": 1.4101150035858154, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6076.68359375, "min": 6076.68359375, "max": 42777.25, "count": 33 }, "Pyramids.Step.mean": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5427449345588684, "min": -0.133658304810524, "max": 0.6147935390472412, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.34034729003906, "min": -31.677017211914062, "max": 172.75698852539062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0015564369969069958, "min": -0.005906177684664726, "max": 0.5428589582443237, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.43113306164741516, "min": -1.5710432529449463, "max": 128.65757751464844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06707062691266936, "min": 0.0664865027796751, "max": 0.07385363970877072, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.938988776777371, "min": 0.48478579704884583, "max": 1.0360435751693633, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014808768251901349, "min": 0.0008708799850595067, "max": 0.017246510391123588, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20732275552661888, "min": 0.007335777905698434, "max": 0.25869765586685384, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.588726041885716e-06, "min": 7.588726041885716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010624216458640003, "min": 0.00010624216458640003, "max": 0.0033773725742092, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252954285714286, "min": 0.10252954285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354136, "min": 1.3691136000000002, "max": 2.4860288, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026270133142857144, "min": 0.00026270133142857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036778186400000003, "min": 0.0036778186400000003, "max": 0.11259650091999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01376793347299099, "min": 0.01376793347299099, "max": 0.6629025340080261, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19275106489658356, "min": 0.19275106489658356, "max": 4.640317916870117, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 342.56976744186045, "min": 301.2315789473684, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29461.0, "min": 15984.0, "max": 31996.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5178650963271774, "min": -1.0000000521540642, "max": 1.63559155722982, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.53639828413725, "min": -32.000001668930054, "max": 155.3811979368329, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5178650963271774, "min": -1.0000000521540642, "max": 1.63559155722982, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.53639828413725, "min": -32.000001668930054, "max": 155.3811979368329, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.048491860370335794, "min": 0.04747070257006654, "max": 13.07496139779687, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.170299991848879, "min": 4.170299991848879, "max": 209.1993823647499, "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": "1687905151", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1687907420" }, "total": 2269.1066641720004, "count": 1, "self": 0.5760810200004016, "children": { "run_training.setup": { "total": 0.07057941200037021, "count": 1, "self": 0.07057941200037021 }, "TrainerController.start_learning": { "total": 2268.4600037399996, "count": 1, "self": 1.3816151739961242, "children": { "TrainerController._reset_env": { "total": 4.749067709999963, "count": 1, "self": 4.749067709999963 }, "TrainerController.advance": { "total": 2262.236313362004, "count": 64032, "self": 1.430788822901377, "children": { "env_step": { "total": 1623.1682355680623, "count": 64032, "self": 1511.4908893400302, "children": { "SubprocessEnvManager._take_step": { "total": 110.87431829598563, "count": 64032, "self": 4.761106101084806, "children": { "TorchPolicy.evaluate": { "total": 106.11321219490083, "count": 62558, "self": 106.11321219490083 } } }, "workers": { "total": 0.8030279320464615, "count": 64032, "self": 0.0, "children": { "worker_root": { "total": 2263.340163677026, "count": 64032, "is_parallel": true, "self": 866.1422354140518, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003528227000060724, "count": 1, "is_parallel": true, "self": 0.0015520129995820753, "children": { "_process_rank_one_or_two_observation": { "total": 0.001976214000478649, "count": 8, "is_parallel": true, "self": 0.001976214000478649 } } }, "UnityEnvironment.step": { "total": 0.04939793699986694, "count": 1, "is_parallel": true, "self": 0.0005373210001380357, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005044259996793699, "count": 1, "is_parallel": true, "self": 0.0005044259996793699 }, "communicator.exchange": { "total": 0.04658426500009227, "count": 1, "is_parallel": true, "self": 0.04658426500009227 }, "steps_from_proto": { "total": 0.001771924999957264, "count": 1, "is_parallel": true, "self": 0.00034567100010463037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014262539998526336, "count": 8, "is_parallel": true, "self": 0.0014262539998526336 } } } } } } }, "UnityEnvironment.step": { "total": 1397.197928262974, "count": 64031, "is_parallel": true, "self": 33.10495772901322, "children": { "UnityEnvironment._generate_step_input": { "total": 22.40305631294632, "count": 64031, "is_parallel": true, "self": 22.40305631294632 }, "communicator.exchange": { "total": 1239.4977482450386, "count": 64031, "is_parallel": true, "self": 1239.4977482450386 }, "steps_from_proto": { "total": 102.19216597597597, "count": 64031, "is_parallel": true, "self": 20.203672994013232, "children": { "_process_rank_one_or_two_observation": { "total": 81.98849298196274, "count": 512248, "is_parallel": true, "self": 81.98849298196274 } } } } } } } } } } }, "trainer_advance": { "total": 637.6372889710401, "count": 64032, "self": 2.520096737950098, "children": { "process_trajectory": { "total": 109.53501341308447, "count": 64032, "self": 109.3282901920852, "children": { "RLTrainer._checkpoint": { "total": 0.20672322099926532, "count": 2, "self": 0.20672322099926532 } } }, "_update_policy": { "total": 525.5821788200055, "count": 447, "self": 335.78254726205296, "children": { "TorchPPOOptimizer.update": { "total": 189.79963155795258, "count": 22818, "self": 189.79963155795258 } } } } } } }, "trainer_threads": { "total": 9.799996405490674e-07, "count": 1, "self": 9.799996405490674e-07 }, "TrainerController._save_models": { "total": 0.09300651400008064, "count": 1, "self": 0.0015150319995882455, "children": { "RLTrainer._checkpoint": { "total": 0.0914914820004924, "count": 1, "self": 0.0914914820004924 } } } } } } }