{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7192228436470032, "min": 0.6814202070236206, "max": 1.4821686744689941, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21542.162109375, "min": 20529.828125, "max": 44963.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.17974357306957245, "min": -0.11352578550577164, "max": 0.17974357306957245, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 45.295379638671875, "min": -27.35971450805664, "max": 45.295379638671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03648325428366661, "min": -0.03648325428366661, "max": 0.2792997360229492, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.193779945373535, "min": -9.193779945373535, "max": 66.19403839111328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06685801928549717, "min": 0.06685801928549717, "max": 0.07325031839157482, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9360122699969604, "min": 0.5117345317733546, "max": 1.0873268810973966, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010475908567342162, "min": 0.00011163550611655083, "max": 0.010475908567342162, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14666271994279026, "min": 0.0014512615795151608, "max": 0.14666271994279026, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2750118607428615e-06, "min": 7.2750118607428615e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010185016605040006, "min": 0.00010185016605040006, "max": 0.0035087843304052995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242497142857145, "min": 0.10242497142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339496000000003, "min": 1.3886848, "max": 2.5695947000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025225464571428585, "min": 0.00025225464571428585, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035315650400000015, "min": 0.0035315650400000015, "max": 0.11698251052999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010733752511441708, "min": 0.010410493239760399, "max": 0.402604341506958, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15027253329753876, "min": 0.14976488053798676, "max": 2.818230390548706, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 652.1739130434783, "min": 652.1739130434783, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30000.0, "min": 15984.0, "max": 33145.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8259347448854343, "min": -1.0000000521540642, "max": 0.8259347448854343, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 37.99299826472998, "min": -31.99640168249607, "max": 37.99299826472998, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8259347448854343, "min": -1.0000000521540642, "max": 0.8259347448854343, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 37.99299826472998, "min": -31.99640168249607, "max": 37.99299826472998, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07305579967847418, "min": 0.07305579967847418, "max": 7.632940627634525, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3605667852098122, "min": 3.193130294501316, "max": 122.1270500421524, "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": "1729301449", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729304361" }, "total": 2911.9007037360007, "count": 1, "self": 0.5796403280000959, "children": { "run_training.setup": { "total": 0.07114815099976113, "count": 1, "self": 0.07114815099976113 }, "TrainerController.start_learning": { "total": 2911.249915257001, "count": 1, "self": 2.3053217980186673, "children": { "TrainerController._reset_env": { "total": 2.3905235980000725, "count": 1, "self": 2.3905235980000725 }, "TrainerController.advance": { "total": 2906.477463718984, "count": 63234, "self": 2.40347424270567, "children": { "env_step": { "total": 1867.8115031531297, "count": 63234, "self": 1715.4886679779047, "children": { "SubprocessEnvManager._take_step": { "total": 150.99164593033493, "count": 63234, "self": 6.562723601292419, "children": { "TorchPolicy.evaluate": { "total": 144.4289223290425, "count": 62556, "self": 144.4289223290425 } } }, "workers": { "total": 1.3311892448900835, "count": 63234, "self": 0.0, "children": { "worker_root": { "total": 2904.586713236903, "count": 63234, "is_parallel": true, "self": 1356.1549520307517, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033131310001408565, "count": 1, "is_parallel": true, "self": 0.001110160998905485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022029700012353715, "count": 8, "is_parallel": true, "self": 0.0022029700012353715 } } }, "UnityEnvironment.step": { "total": 0.06242869700054143, "count": 1, "is_parallel": true, "self": 0.0008265260003099684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00053550400025415, "count": 1, "is_parallel": true, "self": 0.00053550400025415 }, "communicator.exchange": { "total": 0.05896357700021326, "count": 1, "is_parallel": true, "self": 0.05896357700021326 }, "steps_from_proto": { "total": 0.0021030899997640518, "count": 1, "is_parallel": true, "self": 0.000502521000271372, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016005689994926797, "count": 8, "is_parallel": true, "self": 0.0016005689994926797 } } } } } } }, "UnityEnvironment.step": { "total": 1548.4317612061514, "count": 63233, "is_parallel": true, "self": 47.44071844912651, "children": { "UnityEnvironment._generate_step_input": { "total": 29.797714527941025, "count": 63233, "is_parallel": true, "self": 29.797714527941025 }, "communicator.exchange": { "total": 1345.511532765906, "count": 63233, "is_parallel": true, "self": 1345.511532765906 }, "steps_from_proto": { "total": 125.68179546317788, "count": 63233, "is_parallel": true, "self": 27.0220816505489, "children": { "_process_rank_one_or_two_observation": { "total": 98.65971381262898, "count": 505864, "is_parallel": true, "self": 98.65971381262898 } } } } } } } } } } }, "trainer_advance": { "total": 1036.2624863231486, "count": 63234, "self": 4.322292622318855, "children": { "process_trajectory": { "total": 160.63538537981822, "count": 63234, "self": 160.4148888968184, "children": { "RLTrainer._checkpoint": { "total": 0.22049648299980618, "count": 2, "self": 0.22049648299980618 } } }, "_update_policy": { "total": 871.3048083210115, "count": 449, "self": 362.9493422448995, "children": { "TorchPPOOptimizer.update": { "total": 508.35546607611195, "count": 22761, "self": 508.35546607611195 } } } } } } }, "trainer_threads": { "total": 1.6189987945836037e-06, "count": 1, "self": 1.6189987945836037e-06 }, "TrainerController._save_models": { "total": 0.0766045229993324, "count": 1, "self": 0.0018705669990595197, "children": { "RLTrainer._checkpoint": { "total": 0.07473395600027288, "count": 1, "self": 0.07473395600027288 } } } } } } }