{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4398247003555298, "min": 0.4375339150428772, "max": 1.5264146327972412, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13321.41015625, "min": 13028.009765625, "max": 46305.3125, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29902.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29902.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6961135864257812, "min": -0.09869476407766342, "max": 0.7011829018592834, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 203.26516723632812, "min": -23.785438537597656, "max": 203.26516723632812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00200877757743001, "min": 0.00200877757743001, "max": 0.30964818596839905, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5865630507469177, "min": 0.5865630507469177, "max": 73.3866195678711, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06767919764249762, "min": 0.06527426364413084, "max": 0.07469255152834522, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9475087669949668, "min": 0.5609906470613331, "max": 1.062720998992696, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017048817383640977, "min": 0.0007620616460460165, "max": 0.01802328462543931, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23868344337097366, "min": 0.009906801398598213, "max": 0.27034926938158965, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.491076074435711e-06, "min": 7.491076074435711e-06, "max": 0.0002950011016663, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010487506504209995, "min": 0.00010487506504209995, "max": 0.0036328822890393003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10124849642857145, "min": 0.10124849642857145, "max": 0.14916685, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4174789500000002, "min": 1.1933348, "max": 2.00548035, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002594495864285713, "min": 0.0002594495864285713, "max": 0.00983353663, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036322942099999986, "min": 0.0036322942099999986, "max": 0.12111497393000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01145987119525671, "min": 0.011184176430106163, "max": 0.42347705364227295, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1604381948709488, "min": 0.15657846629619598, "max": 3.3878164291381836, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 285.8317757009346, "min": 266.7477477477477, "max": 988.34375, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30584.0, "min": 16189.0, "max": 33434.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6954672809376894, "min": -0.8642312996089458, "max": 1.7332522397911228, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.41499906033278, "min": -28.736801654100418, "max": 193.29159897565842, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6954672809376894, "min": -0.8642312996089458, "max": 1.7332522397911228, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.41499906033278, "min": -28.736801654100418, "max": 193.29159897565842, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03347478735260121, "min": 0.03143202392295263, "max": 9.250461385530585, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.58180224672833, "min": 3.488954655447742, "max": 157.25784355401993, "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": "1680538790", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1680541033" }, "total": 2242.754576104, "count": 1, "self": 0.43708407200028887, "children": { "run_training.setup": { "total": 0.10961587399992823, "count": 1, "self": 0.10961587399992823 }, "TrainerController.start_learning": { "total": 2242.207876158, "count": 1, "self": 1.3633283179465252, "children": { "TrainerController._reset_env": { "total": 4.567000144000076, "count": 1, "self": 4.567000144000076 }, "TrainerController.advance": { "total": 2236.150569294054, "count": 63986, "self": 1.4533385170693691, "children": { "env_step": { "total": 1606.4095086879809, "count": 63986, "self": 1497.4715759690348, "children": { "SubprocessEnvManager._take_step": { "total": 108.09142103594263, "count": 63986, "self": 4.622231880880918, "children": { "TorchPolicy.evaluate": { "total": 103.46918915506171, "count": 62556, "self": 103.46918915506171 } } }, "workers": { "total": 0.8465116830034276, "count": 63986, "self": 0.0, "children": { "worker_root": { "total": 2237.1990363269806, "count": 63986, "is_parallel": true, "self": 849.645000836018, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018710459999056184, "count": 1, "is_parallel": true, "self": 0.0006864629999654426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011845829999401758, "count": 8, "is_parallel": true, "self": 0.0011845829999401758 } } }, "UnityEnvironment.step": { "total": 0.0737499200001821, "count": 1, "is_parallel": true, "self": 0.0005389929999637388, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004685930000505323, "count": 1, "is_parallel": true, "self": 0.0004685930000505323 }, "communicator.exchange": { "total": 0.07097582599999441, "count": 1, "is_parallel": true, "self": 0.07097582599999441 }, "steps_from_proto": { "total": 0.0017665080001734168, "count": 1, "is_parallel": true, "self": 0.00040309800033355714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013634099998398597, "count": 8, "is_parallel": true, "self": 0.0013634099998398597 } } } } } } }, "UnityEnvironment.step": { "total": 1387.5540354909626, "count": 63985, "is_parallel": true, "self": 32.11715278684028, "children": { "UnityEnvironment._generate_step_input": { "total": 22.16129753006794, "count": 63985, "is_parallel": true, "self": 22.16129753006794 }, "communicator.exchange": { "total": 1241.103184416967, "count": 63985, "is_parallel": true, "self": 1241.103184416967 }, "steps_from_proto": { "total": 92.17240075708742, "count": 63985, "is_parallel": true, "self": 19.52233655533746, "children": { "_process_rank_one_or_two_observation": { "total": 72.65006420174996, "count": 511880, "is_parallel": true, "self": 72.65006420174996 } } } } } } } } } } }, "trainer_advance": { "total": 628.2877220890036, "count": 63986, "self": 2.552128341083744, "children": { "process_trajectory": { "total": 104.75684309491999, "count": 63986, "self": 104.4274807939205, "children": { "RLTrainer._checkpoint": { "total": 0.3293623009994917, "count": 2, "self": 0.3293623009994917 } } }, "_update_policy": { "total": 520.9787506529999, "count": 452, "self": 323.86580407498286, "children": { "TorchPPOOptimizer.update": { "total": 197.11294657801704, "count": 22770, "self": 197.11294657801704 } } } } } } }, "trainer_threads": { "total": 9.209998097503558e-07, "count": 1, "self": 9.209998097503558e-07 }, "TrainerController._save_models": { "total": 0.12697748099981254, "count": 1, "self": 0.0020916439998472924, "children": { "RLTrainer._checkpoint": { "total": 0.12488583699996525, "count": 1, "self": 0.12488583699996525 } } } } } } }