{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6108947396278381, "min": 0.5913000702857971, "max": 1.5277938842773438, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18248.6484375, "min": 17644.39453125, "max": 46347.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4226970374584198, "min": -0.15486682951450348, "max": 0.46327686309814453, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.24168395996094, "min": -37.322906494140625, "max": 126.4745864868164, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06831049919128418, "min": -0.12132998555898666, "max": 0.6831167340278625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.78538703918457, "min": -32.15244674682617, "max": 164.63113403320312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.032634509236751395, "min": 0.029665305603495135, "max": 0.04076152978314444, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.22844156465725976, "min": 0.16304611913257777, "max": 0.3054855889931787, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016176609643956737, "min": 0.0016630183671762497, "max": 0.01758412607125051, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11323626750769715, "min": 0.011641128570233748, "max": 0.1330827446266388, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.191054745871432e-06, "min": 7.191054745871432e-06, "max": 0.00029544960151680006, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.0337383221100025e-05, "min": 5.0337383221100025e-05, "max": 0.0019430709523097, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10239698571428572, "min": 0.10239698571428572, "max": 0.19848320000000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7167789000000001, "min": 0.7167789000000001, "max": 1.3476903, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000249458872857143, "min": 0.000249458872857143, "max": 0.009848471680000002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0017462121100000009, "min": 0.0017462121100000009, "max": 0.06477426097, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.029747527092695236, "min": 0.029747527092695236, "max": 0.8650932312011719, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20823268592357635, "min": 0.20823268592357635, "max": 3.5050172805786133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 431.7042253521127, "min": 377.82894736842104, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30651.0, "min": 15984.0, "max": 32187.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4837661767509622, "min": -1.0000000521540642, "max": 1.5290527584859066, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.34739854931831, "min": -29.806601651012897, "max": 115.28279858827591, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4837661767509622, "min": -1.0000000521540642, "max": 1.5290527584859066, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.34739854931831, "min": -29.806601651012897, "max": 115.28279858827591, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13184046082552786, "min": 0.12332039502679866, "max": 11.199776386842132, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 9.360672718612477, "min": 9.360672718612477, "max": 267.5677567124367, "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": "1696036895", "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", "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": "1696038911" }, "total": 2015.474267846, "count": 1, "self": 0.4879589159997977, "children": { "run_training.setup": { "total": 0.04072322100000747, "count": 1, "self": 0.04072322100000747 }, "TrainerController.start_learning": { "total": 2014.9455857090002, "count": 1, "self": 1.388280593952686, "children": { "TrainerController._reset_env": { "total": 4.111138328000152, "count": 1, "self": 4.111138328000152 }, "TrainerController.advance": { "total": 2009.3544861220475, "count": 63702, "self": 1.3551691760085305, "children": { "env_step": { "total": 1535.2195172810102, "count": 63702, "self": 1426.2943200390343, "children": { "SubprocessEnvManager._take_step": { "total": 108.12746983500097, "count": 63702, "self": 4.809192913028255, "children": { "TorchPolicy.evaluate": { "total": 103.31827692197271, "count": 62559, "self": 103.31827692197271 } } }, "workers": { "total": 0.7977274069749001, "count": 63702, "self": 0.0, "children": { "worker_root": { "total": 2010.0421969169759, "count": 63702, "is_parallel": true, "self": 698.2265860330217, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018294110000169894, "count": 1, "is_parallel": true, "self": 0.0005624410000564239, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012669699999605655, "count": 8, "is_parallel": true, "self": 0.0012669699999605655 } } }, "UnityEnvironment.step": { "total": 0.05321653200007859, "count": 1, "is_parallel": true, "self": 0.0006318380001175683, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000662981999994372, "count": 1, "is_parallel": true, "self": 0.000662981999994372 }, "communicator.exchange": { "total": 0.049185785999952714, "count": 1, "is_parallel": true, "self": 0.049185785999952714 }, "steps_from_proto": { "total": 0.002735926000013933, "count": 1, "is_parallel": true, "self": 0.00035638199983623053, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023795440001777024, "count": 8, "is_parallel": true, "self": 0.0023795440001777024 } } } } } } }, "UnityEnvironment.step": { "total": 1311.8156108839542, "count": 63701, "is_parallel": true, "self": 34.22474295986899, "children": { "UnityEnvironment._generate_step_input": { "total": 22.772985178032513, "count": 63701, "is_parallel": true, "self": 22.772985178032513 }, "communicator.exchange": { "total": 1148.8495001020651, "count": 63701, "is_parallel": true, "self": 1148.8495001020651 }, "steps_from_proto": { "total": 105.96838264398752, "count": 63701, "is_parallel": true, "self": 20.5462574791527, "children": { "_process_rank_one_or_two_observation": { "total": 85.42212516483482, "count": 509608, "is_parallel": true, "self": 85.42212516483482 } } } } } } } } } } }, "trainer_advance": { "total": 472.7797996650288, "count": 63702, "self": 2.5116337910337734, "children": { "process_trajectory": { "total": 113.11816792499417, "count": 63702, "self": 112.91474547499433, "children": { "RLTrainer._checkpoint": { "total": 0.2034224499998345, "count": 2, "self": 0.2034224499998345 } } }, "_update_policy": { "total": 357.14999794900086, "count": 234, "self": 295.83719117899045, "children": { "TorchPPOOptimizer.update": { "total": 61.31280677001041, "count": 5736, "self": 61.31280677001041 } } } } } } }, "trainer_threads": { "total": 1.4150000424706377e-06, "count": 1, "self": 1.4150000424706377e-06 }, "TrainerController._save_models": { "total": 0.09167924999974275, "count": 1, "self": 0.0013463619998219656, "children": { "RLTrainer._checkpoint": { "total": 0.09033288799992079, "count": 1, "self": 0.09033288799992079 } } } } } } }