{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2815791368484497, "min": 0.26410967111587524, "max": 1.4433350563049316, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8420.3427734375, "min": 7952.8701171875, "max": 43785.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6340747475624084, "min": -0.12323407828807831, "max": 0.6357510685920715, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 179.44314575195312, "min": -29.57617950439453, "max": 180.19476318359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006997785065323114, "min": -0.006997785065323114, "max": 0.4847884178161621, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.9803731441497803, "min": -1.9803731441497803, "max": 114.89485168457031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06771040390788888, "min": 0.06565829043262586, "max": 0.07423109274693869, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0156560586183332, "min": 0.5014007827912688, "max": 1.073355843549293, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013978243890991495, "min": 0.00048400736985462317, "max": 0.015833817790715125, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20967365836487242, "min": 0.005808088438255478, "max": 0.2375072668607269, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.508037497353334e-06, "min": 7.508037497353334e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001126205624603, "min": 0.0001126205624603, "max": 0.0035087528304158, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025026466666667, "min": 0.1025026466666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375397000000004, "min": 1.3886848, "max": 2.5695842000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000260014402, "min": 0.000260014402, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039002160299999996, "min": 0.0039002160299999996, "max": 0.11698146158, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011765619739890099, "min": 0.011765619739890099, "max": 0.47923702001571655, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17648430168628693, "min": 0.17331907153129578, "max": 3.354659080505371, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 324.7956989247312, "min": 309.03125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30206.0, "min": 15984.0, "max": 32943.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.610679548434032, "min": -1.0000000521540642, "max": 1.610679548434032, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.79319800436497, "min": -29.897601634263992, "max": 163.33459869027138, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.610679548434032, "min": -1.0000000521540642, "max": 1.610679548434032, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.79319800436497, "min": -29.897601634263992, "max": 163.33459869027138, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04013715205123893, "min": 0.039013729638933604, "max": 9.595420572906733, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.732755140765221, "min": 3.637642389527173, "max": 153.52672916650772, "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": "1751681982", "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--force --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": "1751684198" }, "total": 2216.349738875, "count": 1, "self": 0.5000486310000269, "children": { "run_training.setup": { "total": 0.020424682999873767, "count": 1, "self": 0.020424682999873767 }, "TrainerController.start_learning": { "total": 2215.8292655610003, "count": 1, "self": 1.3335424570263967, "children": { "TrainerController._reset_env": { "total": 2.259902538999995, "count": 1, "self": 2.259902538999995 }, "TrainerController.advance": { "total": 2212.1512341039743, "count": 63913, "self": 1.5252757710832157, "children": { "env_step": { "total": 1563.0030217729068, "count": 63913, "self": 1410.9820126908307, "children": { "SubprocessEnvManager._take_step": { "total": 151.1900411480524, "count": 63913, "self": 4.643048821046705, "children": { "TorchPolicy.evaluate": { "total": 146.54699232700568, "count": 62562, "self": 146.54699232700568 } } }, "workers": { "total": 0.8309679340236471, "count": 63913, "self": 0.0, "children": { "worker_root": { "total": 2210.34583594405, "count": 63913, "is_parallel": true, "self": 914.5653786050652, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018950979999772244, "count": 1, "is_parallel": true, "self": 0.0006416309997803182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012534670001969062, "count": 8, "is_parallel": true, "self": 0.0012534670001969062 } } }, "UnityEnvironment.step": { "total": 0.0472627530000409, "count": 1, "is_parallel": true, "self": 0.0005265940001208946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004924019999634766, "count": 1, "is_parallel": true, "self": 0.0004924019999634766 }, "communicator.exchange": { "total": 0.044191999000076976, "count": 1, "is_parallel": true, "self": 0.044191999000076976 }, "steps_from_proto": { "total": 0.0020517579998795554, "count": 1, "is_parallel": true, "self": 0.0004183440000815608, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016334139997979946, "count": 8, "is_parallel": true, "self": 0.0016334139997979946 } } } } } } }, "UnityEnvironment.step": { "total": 1295.780457338985, "count": 63912, "is_parallel": true, "self": 31.95620804500186, "children": { "UnityEnvironment._generate_step_input": { "total": 23.218502664010657, "count": 63912, "is_parallel": true, "self": 23.218502664010657 }, "communicator.exchange": { "total": 1143.4281385669956, "count": 63912, "is_parallel": true, "self": 1143.4281385669956 }, "steps_from_proto": { "total": 97.17760806297679, "count": 63912, "is_parallel": true, "self": 19.755029070046703, "children": { "_process_rank_one_or_two_observation": { "total": 77.42257899293008, "count": 511296, "is_parallel": true, "self": 77.42257899293008 } } } } } } } } } } }, "trainer_advance": { "total": 647.6229365599845, "count": 63913, "self": 2.6369402880091, "children": { "process_trajectory": { "total": 126.06523323996976, "count": 63913, "self": 125.8632770749698, "children": { "RLTrainer._checkpoint": { "total": 0.20195616499995594, "count": 2, "self": 0.20195616499995594 } } }, "_update_policy": { "total": 518.9207630320057, "count": 452, "self": 289.5463617950211, "children": { "TorchPPOOptimizer.update": { "total": 229.37440123698457, "count": 22794, "self": 229.37440123698457 } } } } } } }, "trainer_threads": { "total": 1.1009997251676396e-06, "count": 1, "self": 1.1009997251676396e-06 }, "TrainerController._save_models": { "total": 0.08458535999989181, "count": 1, "self": 0.0011138629997731186, "children": { "RLTrainer._checkpoint": { "total": 0.08347149700011869, "count": 1, "self": 0.08347149700011869 } } } } } } }