{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15530835092067719, "min": 0.1444583535194397, "max": 1.4827940464019775, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4644.3408203125, "min": 4343.287109375, "max": 44982.0390625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999959.0, "min": 29925.0, "max": 2999959.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999959.0, "min": 29925.0, "max": 2999959.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7832499742507935, "min": -0.10904666036367416, "max": 0.8337348699569702, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 228.708984375, "min": -26.280244827270508, "max": 250.95419311523438, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003057679394260049, "min": -0.09043258428573608, "max": 0.3513456881046295, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8928424119949341, "min": -26.858478546142578, "max": 83.26892852783203, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0675028619000278, "min": 0.06071041038376279, "max": 0.07530202114555452, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9450400666003892, "min": 0.5228269274828918, "max": 1.0716459741039823, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01584337667113037, "min": 0.00019019137004627453, "max": 0.01620345738224892, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22180727339582518, "min": 0.0024724878106015687, "max": 0.24305186073373383, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4345709504142845e-06, "min": 1.4345709504142845e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0083993305799982e-05, "min": 2.0083993305799982e-05, "max": 0.0039692712769096, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047815714285716, "min": 0.10047815714285716, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066942000000002, "min": 1.3962282666666668, "max": 2.7825241333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.776789857142854e-05, "min": 5.776789857142854e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008087505799999995, "min": 0.0008087505799999995, "max": 0.13231673096, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007444213144481182, "min": 0.006976852659136057, "max": 0.5011016726493835, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1042189821600914, "min": 0.10048458725214005, "max": 3.507711887359619, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 219.92700729927006, "min": 216.11347517730496, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30130.0, "min": 16852.0, "max": 33909.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.765468599152391, "min": -0.9998645681527353, "max": 1.7848285559032644, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 241.86919808387756, "min": -31.995201662182808, "max": 249.87599782645702, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.765468599152391, "min": -0.9998645681527353, "max": 1.7848285559032644, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 241.86919808387756, "min": -31.995201662182808, "max": 249.87599782645702, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01666211066546639, "min": 0.01666211066546639, "max": 9.957700459396138, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2827091611688957, "min": 2.1751220718538207, "max": 169.28090780973434, "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": "1693713857", "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 Training --no-graphics --force", "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": "1693725180" }, "total": 11322.372708220999, "count": 1, "self": 1.64395342699936, "children": { "run_training.setup": { "total": 0.09038556299947231, "count": 1, "self": 0.09038556299947231 }, "TrainerController.start_learning": { "total": 11320.638369231001, "count": 1, "self": 8.670951521142342, "children": { "TrainerController._reset_env": { "total": 6.024486048999279, "count": 1, "self": 6.024486048999279 }, "TrainerController.advance": { "total": 11305.76283192786, "count": 195162, "self": 8.532811325840157, "children": { "env_step": { "total": 7473.175218789936, "count": 195162, "self": 6774.635841417312, "children": { "SubprocessEnvManager._take_step": { "total": 693.895807741892, "count": 195162, "self": 26.897441243940193, "children": { "TorchPolicy.evaluate": { "total": 666.9983664979518, "count": 187559, "self": 666.9983664979518 } } }, "workers": { "total": 4.64356963073169, "count": 195162, "self": 0.0, "children": { "worker_root": { "total": 11302.396405085612, "count": 195162, "is_parallel": true, "self": 5153.346856361247, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002513078999982099, "count": 1, "is_parallel": true, "self": 0.0006987059987295652, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018143730012525339, "count": 8, "is_parallel": true, "self": 0.0018143730012525339 } } }, "UnityEnvironment.step": { "total": 0.09015176799948676, "count": 1, "is_parallel": true, "self": 0.0006873489983263426, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006106850005380693, "count": 1, "is_parallel": true, "self": 0.0006106850005380693 }, "communicator.exchange": { "total": 0.08674075300041295, "count": 1, "is_parallel": true, "self": 0.08674075300041295 }, "steps_from_proto": { "total": 0.002112981000209402, "count": 1, "is_parallel": true, "self": 0.00041465799949946813, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016983230007099337, "count": 8, "is_parallel": true, "self": 0.0016983230007099337 } } } } } } }, "UnityEnvironment.step": { "total": 6149.049548724365, "count": 195161, "is_parallel": true, "self": 115.77159402948018, "children": { "UnityEnvironment._generate_step_input": { "total": 79.94626410559704, "count": 195161, "is_parallel": true, "self": 79.94626410559704 }, "communicator.exchange": { "total": 5556.428740675854, "count": 195161, "is_parallel": true, "self": 5556.428740675854 }, "steps_from_proto": { "total": 396.902949913434, "count": 195161, "is_parallel": true, "self": 84.28265557494797, "children": { "_process_rank_one_or_two_observation": { "total": 312.620294338486, "count": 1561288, "is_parallel": true, "self": 312.620294338486 } } } } } } } } } } }, "trainer_advance": { "total": 3824.0548018120835, "count": 195162, "self": 15.744055129970548, "children": { "process_trajectory": { "total": 733.4857914681161, "count": 195162, "self": 732.0334956951147, "children": { "RLTrainer._checkpoint": { "total": 1.452295773001424, "count": 6, "self": 1.452295773001424 } } }, "_update_policy": { "total": 3074.824955213997, "count": 1401, "self": 2017.9901011370293, "children": { "TorchPPOOptimizer.update": { "total": 1056.8348540769675, "count": 68331, "self": 1056.8348540769675 } } } } } } }, "trainer_threads": { "total": 2.151000444428064e-06, "count": 1, "self": 2.151000444428064e-06 }, "TrainerController._save_models": { "total": 0.18009758200059878, "count": 1, "self": 0.002011648000916466, "children": { "RLTrainer._checkpoint": { "total": 0.1780859339996823, "count": 1, "self": 0.1780859339996823 } } } } } } }