{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3916018605232239, "min": 0.3916018605232239, "max": 1.5255680084228516, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11691.6650390625, "min": 11691.6650390625, "max": 46279.6328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5317308306694031, "min": -0.2037552446126938, "max": 0.616454005241394, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.69424438476562, "min": -48.28999328613281, "max": 177.53875732421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019445765763521194, "min": -0.004623772576451302, "max": 0.2790747880935669, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.328139781951904, "min": -1.2622898817062378, "max": 67.25702667236328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07039987765095984, "min": 0.06634647107398768, "max": 0.07453225501215446, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9855982871134378, "min": 0.4872511159488129, "max": 1.085462998957761, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013232231376432105, "min": 0.0003553888858543645, "max": 0.017123908590944748, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18525123927004947, "min": 0.0039092777443980094, "max": 0.23973472027322645, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4211546691714284e-06, "min": 7.4211546691714284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001038961653684, "min": 0.0001038961653684, "max": 0.0035083217305595, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247368571428572, "min": 0.10247368571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346316000000001, "min": 1.3886848, "max": 2.5694405, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025712120285714283, "min": 0.00025712120285714283, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035996968399999996, "min": 0.0035996968399999996, "max": 0.11696710595, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01076093316078186, "min": 0.01076093316078186, "max": 0.41235366463661194, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15065306425094604, "min": 0.15065306425094604, "max": 2.8864755630493164, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.8192771084337, "min": 314.2551020408163, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29201.0, "min": 15984.0, "max": 32653.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5828731505245697, "min": -1.0000000521540642, "max": 1.6633999747388504, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 129.79559834301472, "min": -31.998001664876938, "max": 161.2011980637908, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5828731505245697, "min": -1.0000000521540642, "max": 1.6633999747388504, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 129.79559834301472, "min": -31.998001664876938, "max": 161.2011980637908, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03860677600229193, "min": 0.03577725406515184, "max": 8.382938785478473, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1657556321879383, "min": 3.1657556321879383, "max": 134.12702056765556, "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": "1714839625", "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=Pyramids Training --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": "1714842871" }, "total": 3245.2284925500003, "count": 1, "self": 0.5921371579997867, "children": { "run_training.setup": { "total": 0.0684085830002914, "count": 1, "self": 0.0684085830002914 }, "TrainerController.start_learning": { "total": 3244.567946809, "count": 1, "self": 2.3974859270506386, "children": { "TrainerController._reset_env": { "total": 2.9988253789997543, "count": 1, "self": 2.9988253789997543 }, "TrainerController.advance": { "total": 3239.0859749429505, "count": 63898, "self": 2.567804683816121, "children": { "env_step": { "total": 2157.8447118880636, "count": 63898, "self": 1994.5278140288783, "children": { "SubprocessEnvManager._take_step": { "total": 161.79709887305535, "count": 63898, "self": 7.345319109120737, "children": { "TorchPolicy.evaluate": { "total": 154.4517797639346, "count": 62552, "self": 154.4517797639346 } } }, "workers": { "total": 1.5197989861298993, "count": 63898, "self": 0.0, "children": { "worker_root": { "total": 3236.9201164729025, "count": 63898, "is_parallel": true, "self": 1436.9489332078938, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003217592000055447, "count": 1, "is_parallel": true, "self": 0.0010329300002922537, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021846619997631933, "count": 8, "is_parallel": true, "self": 0.0021846619997631933 } } }, "UnityEnvironment.step": { "total": 0.061928099999931874, "count": 1, "is_parallel": true, "self": 0.0007641220004188654, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005156869997335889, "count": 1, "is_parallel": true, "self": 0.0005156869997335889 }, "communicator.exchange": { "total": 0.05869145899987416, "count": 1, "is_parallel": true, "self": 0.05869145899987416 }, "steps_from_proto": { "total": 0.001956831999905262, "count": 1, "is_parallel": true, "self": 0.00041677399985928787, "children": { "_process_rank_one_or_two_observation": { "total": 0.001540058000045974, "count": 8, "is_parallel": true, "self": 0.001540058000045974 } } } } } } }, "UnityEnvironment.step": { "total": 1799.9711832650087, "count": 63897, "is_parallel": true, "self": 52.27284569900212, "children": { "UnityEnvironment._generate_step_input": { "total": 32.771382612083016, "count": 63897, "is_parallel": true, "self": 32.771382612083016 }, "communicator.exchange": { "total": 1583.9167560420424, "count": 63897, "is_parallel": true, "self": 1583.9167560420424 }, "steps_from_proto": { "total": 131.01019891188116, "count": 63897, "is_parallel": true, "self": 28.44444860911699, "children": { "_process_rank_one_or_two_observation": { "total": 102.56575030276417, "count": 511176, "is_parallel": true, "self": 102.56575030276417 } } } } } } } } } } }, "trainer_advance": { "total": 1078.6734583710709, "count": 63898, "self": 4.925437671177406, "children": { "process_trajectory": { "total": 172.3175672638945, "count": 63898, "self": 172.1186475078939, "children": { "RLTrainer._checkpoint": { "total": 0.19891975600057776, "count": 2, "self": 0.19891975600057776 } } }, "_update_policy": { "total": 901.430453435999, "count": 448, "self": 364.376821782967, "children": { "TorchPPOOptimizer.update": { "total": 537.053631653032, "count": 22830, "self": 537.053631653032 } } } } } } }, "trainer_threads": { "total": 1.4669994925498031e-06, "count": 1, "self": 1.4669994925498031e-06 }, "TrainerController._save_models": { "total": 0.08565909299977648, "count": 1, "self": 0.002020752000134962, "children": { "RLTrainer._checkpoint": { "total": 0.08363834099964151, "count": 1, "self": 0.08363834099964151 } } } } } } }