{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4898530840873718, "min": 0.4898530840873718, "max": 1.4597269296646118, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14468.30078125, "min": 14468.30078125, "max": 44282.27734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5242120027542114, "min": -0.10135825723409653, "max": 0.5393515825271606, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.58566284179688, "min": -24.021907806396484, "max": 149.9397430419922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0468950979411602, "min": -0.008637974038720131, "max": 0.27787673473358154, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.75546646118164, "min": -2.3754429817199707, "max": 65.8567886352539, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0666500309640209, "min": 0.06509060273436093, "max": 0.07368036173916173, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9331004334962926, "min": 0.5005849991863508, "max": 1.0753547204841, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012792011675108888, "min": 0.00045996042416941306, "max": 0.014765001286317659, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17908816345152442, "min": 0.00597948551420237, "max": 0.20995428126679694, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.672897442400002e-06, "min": 7.672897442400002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010742056419360001, "min": 0.00010742056419360001, "max": 0.0032589209136930993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025576, "min": 0.1025576, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358064, "min": 1.3886848, "max": 2.3863069, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026550424000000003, "min": 0.00026550424000000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037170593600000007, "min": 0.0037170593600000007, "max": 0.10865205931000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009835271164774895, "min": 0.009835271164774895, "max": 0.432793527841568, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13769379258155823, "min": 0.13769379258155823, "max": 3.029554605484009, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 387.30263157894734, "min": 342.3222222222222, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29435.0, "min": 15984.0, "max": 33272.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5337184027425552, "min": -1.0000000521540642, "max": 1.598479469330647, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 116.5625986084342, "min": -30.421001628041267, "max": 140.98299837112427, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5337184027425552, "min": -1.0000000521540642, "max": 1.598479469330647, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 116.5625986084342, "min": -30.421001628041267, "max": 140.98299837112427, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039530485409685706, "min": 0.03570412512763741, "max": 8.824089393950999, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0043168911361136, "min": 3.0043168911361136, "max": 141.18543030321598, "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": "1710675547", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Pyramids1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710677845" }, "total": 2297.841387388, "count": 1, "self": 0.5389000929999384, "children": { "run_training.setup": { "total": 0.05373051700007636, "count": 1, "self": 0.05373051700007636 }, "TrainerController.start_learning": { "total": 2297.248756778, "count": 1, "self": 1.7070140439564057, "children": { "TrainerController._reset_env": { "total": 2.1621382069997708, "count": 1, "self": 2.1621382069997708 }, "TrainerController.advance": { "total": 2293.2891274790445, "count": 63690, "self": 1.8431666300448342, "children": { "env_step": { "total": 1649.3678321719817, "count": 63690, "self": 1500.1751562039435, "children": { "SubprocessEnvManager._take_step": { "total": 148.18717493394615, "count": 63690, "self": 5.280864305913383, "children": { "TorchPolicy.evaluate": { "total": 142.90631062803277, "count": 62571, "self": 142.90631062803277 } } }, "workers": { "total": 1.005501034092049, "count": 63690, "self": 0.0, "children": { "worker_root": { "total": 2291.5493357450905, "count": 63690, "is_parallel": true, "self": 930.5209319392752, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002160248000109277, "count": 1, "is_parallel": true, "self": 0.0006467330003943061, "children": { "_process_rank_one_or_two_observation": { "total": 0.001513514999714971, "count": 8, "is_parallel": true, "self": 0.001513514999714971 } } }, "UnityEnvironment.step": { "total": 0.05015199500030576, "count": 1, "is_parallel": true, "self": 0.0006831379996583564, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005895310005143983, "count": 1, "is_parallel": true, "self": 0.0005895310005143983 }, "communicator.exchange": { "total": 0.04700249300003634, "count": 1, "is_parallel": true, "self": 0.04700249300003634 }, "steps_from_proto": { "total": 0.001876833000096667, "count": 1, "is_parallel": true, "self": 0.0005084100002932246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013684229998034425, "count": 8, "is_parallel": true, "self": 0.0013684229998034425 } } } } } } }, "UnityEnvironment.step": { "total": 1361.0284038058153, "count": 63689, "is_parallel": true, "self": 37.43852094562499, "children": { "UnityEnvironment._generate_step_input": { "total": 25.823743519000345, "count": 63689, "is_parallel": true, "self": 25.823743519000345 }, "communicator.exchange": { "total": 1188.1650359781033, "count": 63689, "is_parallel": true, "self": 1188.1650359781033 }, "steps_from_proto": { "total": 109.60110336308662, "count": 63689, "is_parallel": true, "self": 23.25418947385424, "children": { "_process_rank_one_or_two_observation": { "total": 86.34691388923238, "count": 509512, "is_parallel": true, "self": 86.34691388923238 } } } } } } } } } } }, "trainer_advance": { "total": 642.078128677018, "count": 63690, "self": 3.009731366948472, "children": { "process_trajectory": { "total": 133.70026653807054, "count": 63690, "self": 133.4388782410706, "children": { "RLTrainer._checkpoint": { "total": 0.2613882969999395, "count": 2, "self": 0.2613882969999395 } } }, "_update_policy": { "total": 505.36813077199895, "count": 444, "self": 297.266395845998, "children": { "TorchPPOOptimizer.update": { "total": 208.10173492600097, "count": 22815, "self": 208.10173492600097 } } } } } } }, "trainer_threads": { "total": 1.1439997251727618e-06, "count": 1, "self": 1.1439997251727618e-06 }, "TrainerController._save_models": { "total": 0.09047590399950423, "count": 1, "self": 0.0016013469994504703, "children": { "RLTrainer._checkpoint": { "total": 0.08887455700005376, "count": 1, "self": 0.08887455700005376 } } } } } } }