{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4711536169052124, "min": 0.4711536169052124, "max": 1.466884970664978, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14096.916015625, "min": 14096.916015625, "max": 44499.421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.448026567697525, "min": -0.06842176616191864, "max": 0.49583306908607483, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.17506408691406, "min": -16.42122459411621, "max": 135.3624267578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06750607490539551, "min": -0.02575722709298134, "max": 0.3148564398288727, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 17.956615447998047, "min": -6.542335510253906, "max": 75.88040161132812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06781011274493207, "min": 0.06563065249539257, "max": 0.07204657907957383, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9493415784290489, "min": 0.5043260535570169, "max": 1.0341495422277756, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013732771563839936, "min": 0.0014359762829696293, "max": 0.01483793187365053, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1922588018937591, "min": 0.012923786546726664, "max": 0.20773104623110744, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.32140470242143e-06, "min": 7.32140470242143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010249966583390001, "min": 0.00010249966583390001, "max": 0.0035075267308245, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244043571428571, "min": 0.10244043571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341660999999999, "min": 1.3886848, "max": 2.6175326, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025379952785714284, "min": 0.00025379952785714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00355319339, "min": 0.00355319339, "max": 0.11694063245000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008161289617419243, "min": 0.008161289617419243, "max": 0.5603591799736023, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1142580509185791, "min": 0.1142580509185791, "max": 3.9225142002105713, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 449.25396825396825, "min": 391.65384615384613, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28303.0, "min": 15984.0, "max": 32938.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4661110882011672, "min": -1.0000000521540642, "max": 1.4983384331831566, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 92.36499855667353, "min": -30.6680016964674, "max": 115.17279790341854, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4661110882011672, "min": -1.0000000521540642, "max": 1.4983384331831566, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 92.36499855667353, "min": -30.6680016964674, "max": 115.17279790341854, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03724630096246348, "min": 0.035740739162018795, "max": 12.488204099237919, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.346516960635199, "min": 2.346516960635199, "max": 199.8112655878067, "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": "1751519178", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751522500" }, "total": 3322.209400447, "count": 1, "self": 0.6838271969991183, "children": { "run_training.setup": { "total": 0.037656448999769054, "count": 1, "self": 0.037656448999769054 }, "TrainerController.start_learning": { "total": 3321.487916801001, "count": 1, "self": 2.40873323210144, "children": { "TrainerController._reset_env": { "total": 3.789782269999705, "count": 1, "self": 3.789782269999705 }, "TrainerController.advance": { "total": 3315.2129350829, "count": 63636, "self": 2.636079729096309, "children": { "env_step": { "total": 2238.1789328939703, "count": 63636, "self": 2078.409720025593, "children": { "SubprocessEnvManager._take_step": { "total": 158.36140577018887, "count": 63636, "self": 7.322921717024656, "children": { "TorchPolicy.evaluate": { "total": 151.0384840531642, "count": 62554, "self": 151.0384840531642 } } }, "workers": { "total": 1.4078070981886412, "count": 63636, "self": 0.0, "children": { "worker_root": { "total": 3311.644297027795, "count": 63636, "is_parallel": true, "self": 1418.1824093279392, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003521293001540471, "count": 1, "is_parallel": true, "self": 0.000919574002182344, "children": { "_process_rank_one_or_two_observation": { "total": 0.002601718999358127, "count": 8, "is_parallel": true, "self": 0.002601718999358127 } } }, "UnityEnvironment.step": { "total": 0.10719879300086177, "count": 1, "is_parallel": true, "self": 0.0006621280008403119, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005278940006974153, "count": 1, "is_parallel": true, "self": 0.0005278940006974153 }, "communicator.exchange": { "total": 0.10408079800072301, "count": 1, "is_parallel": true, "self": 0.10408079800072301 }, "steps_from_proto": { "total": 0.0019279729986010352, "count": 1, "is_parallel": true, "self": 0.00039776899939170107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015302039992093341, "count": 8, "is_parallel": true, "self": 0.0015302039992093341 } } } } } } }, "UnityEnvironment.step": { "total": 1893.4618876998557, "count": 63635, "is_parallel": true, "self": 46.2804513137271, "children": { "UnityEnvironment._generate_step_input": { "total": 30.53516431395292, "count": 63635, "is_parallel": true, "self": 30.53516431395292 }, "communicator.exchange": { "total": 1687.7468095542354, "count": 63635, "is_parallel": true, "self": 1687.7468095542354 }, "steps_from_proto": { "total": 128.89946251794026, "count": 63635, "is_parallel": true, "self": 28.128140243616144, "children": { "_process_rank_one_or_two_observation": { "total": 100.77132227432412, "count": 509080, "is_parallel": true, "self": 100.77132227432412 } } } } } } } } } } }, "trainer_advance": { "total": 1074.3979224598334, "count": 63636, "self": 4.5107122797435295, "children": { "process_trajectory": { "total": 165.1132323400925, "count": 63636, "self": 164.91591523209172, "children": { "RLTrainer._checkpoint": { "total": 0.19731710800078872, "count": 2, "self": 0.19731710800078872 } } }, "_update_policy": { "total": 904.7739778399973, "count": 445, "self": 368.98644350985705, "children": { "TorchPPOOptimizer.update": { "total": 535.7875343301403, "count": 22755, "self": 535.7875343301403 } } } } } } }, "trainer_threads": { "total": 1.0710009519243613e-06, "count": 1, "self": 1.0710009519243613e-06 }, "TrainerController._save_models": { "total": 0.07646514499901969, "count": 1, "self": 0.0022050689985917415, "children": { "RLTrainer._checkpoint": { "total": 0.07426007600042794, "count": 1, "self": 0.07426007600042794 } } } } } } }