{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4727168083190918, "min": 0.4668564200401306, "max": 1.4380537271499634, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14113.4326171875, "min": 14113.4326171875, "max": 43624.796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.35837605595588684, "min": -0.1177886575460434, "max": 0.44729775190353394, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 94.61128234863281, "min": -28.269277572631836, "max": 121.21768951416016, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.784088671207428, "min": -0.784088671207428, "max": 0.47723692655563354, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -206.99940490722656, "min": -206.99940490722656, "max": 113.10514831542969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06847039740698944, "min": 0.06313184063199696, "max": 0.07422670777199605, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9585855636978522, "min": 0.5073882453361039, "max": 1.106221479033896, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0900324686372187, "min": 0.0003796778554949845, "max": 0.0900324686372187, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.2604545609210618, "min": 0.003796778554949845, "max": 1.2604545609210618, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.548997483700004e-06, "min": 7.548997483700004e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010568596477180005, "min": 0.00010568596477180005, "max": 0.0032225635258121997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025163, "min": 0.1025163, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352282, "min": 1.3886848, "max": 2.4014488000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613783700000001, "min": 0.0002613783700000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003659297180000001, "min": 0.003659297180000001, "max": 0.10743136122000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007867591455578804, "min": 0.007490986026823521, "max": 0.4280175268650055, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11014627665281296, "min": 0.10487380623817444, "max": 2.9961225986480713, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 439.02941176470586, "min": 384.97435897435895, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29854.0, "min": 15984.0, "max": 32645.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.349920561975416, "min": -1.0000000521540642, "max": 1.486789723428396, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 91.79459821432829, "min": -31.998401671648026, "max": 115.9695984274149, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.349920561975416, "min": -1.0000000521540642, "max": 1.486789723428396, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 91.79459821432829, "min": -31.998401671648026, "max": 115.9695984274149, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036555427375466985, "min": 0.03209697372722076, "max": 7.841193682514131, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.485769061531755, "min": 2.0542063185421284, "max": 125.4590989202261, "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": "1713393420", "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": "1713395594" }, "total": 2173.369327259, "count": 1, "self": 0.47695288099976096, "children": { "run_training.setup": { "total": 0.051612536999982694, "count": 1, "self": 0.051612536999982694 }, "TrainerController.start_learning": { "total": 2172.840761841, "count": 1, "self": 1.2191315650252363, "children": { "TrainerController._reset_env": { "total": 2.652315569999928, "count": 1, "self": 2.652315569999928 }, "TrainerController.advance": { "total": 2168.881263368975, "count": 63542, "self": 1.294840020985248, "children": { "env_step": { "total": 1542.4986456399622, "count": 63542, "self": 1417.6290845979204, "children": { "SubprocessEnvManager._take_step": { "total": 124.08987151099245, "count": 63542, "self": 4.550617867013443, "children": { "TorchPolicy.evaluate": { "total": 119.53925364397901, "count": 62558, "self": 119.53925364397901 } } }, "workers": { "total": 0.779689531049371, "count": 63542, "self": 0.0, "children": { "worker_root": { "total": 2167.889959474969, "count": 63542, "is_parallel": true, "self": 865.1798041769789, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020257750002201647, "count": 1, "is_parallel": true, "self": 0.0005814740000005258, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014443010002196388, "count": 8, "is_parallel": true, "self": 0.0014443010002196388 } } }, "UnityEnvironment.step": { "total": 0.08197956300000442, "count": 1, "is_parallel": true, "self": 0.0006672190002063871, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004807719999462279, "count": 1, "is_parallel": true, "self": 0.0004807719999462279 }, "communicator.exchange": { "total": 0.07911591199990653, "count": 1, "is_parallel": true, "self": 0.07911591199990653 }, "steps_from_proto": { "total": 0.0017156599999452737, "count": 1, "is_parallel": true, "self": 0.00035835900007441523, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013573009998708585, "count": 8, "is_parallel": true, "self": 0.0013573009998708585 } } } } } } }, "UnityEnvironment.step": { "total": 1302.7101552979902, "count": 63541, "is_parallel": true, "self": 33.58273039402866, "children": { "UnityEnvironment._generate_step_input": { "total": 23.431059582012267, "count": 63541, "is_parallel": true, "self": 23.431059582012267 }, "communicator.exchange": { "total": 1147.5379025179664, "count": 63541, "is_parallel": true, "self": 1147.5379025179664 }, "steps_from_proto": { "total": 98.15846280398296, "count": 63541, "is_parallel": true, "self": 19.289268883912655, "children": { "_process_rank_one_or_two_observation": { "total": 78.8691939200703, "count": 508328, "is_parallel": true, "self": 78.8691939200703 } } } } } } } } } } }, "trainer_advance": { "total": 625.0877777080277, "count": 63542, "self": 2.351065381956232, "children": { "process_trajectory": { "total": 125.70774465406475, "count": 63542, "self": 125.51505317806459, "children": { "RLTrainer._checkpoint": { "total": 0.19269147600016368, "count": 2, "self": 0.19269147600016368 } } }, "_update_policy": { "total": 497.02896767200673, "count": 444, "self": 293.0419120150186, "children": { "TorchPPOOptimizer.update": { "total": 203.9870556569881, "count": 22833, "self": 203.9870556569881 } } } } } } }, "trainer_threads": { "total": 8.450001587334555e-07, "count": 1, "self": 8.450001587334555e-07 }, "TrainerController._save_models": { "total": 0.08805049200009307, "count": 1, "self": 0.0014504620003208402, "children": { "RLTrainer._checkpoint": { "total": 0.08660002999977223, "count": 1, "self": 0.08660002999977223 } } } } } } }