{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4416777491569519, "min": 0.4416777491569519, "max": 1.479617714881897, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13335.134765625, "min": 13335.134765625, "max": 44885.68359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5572459101676941, "min": -0.11181166023015976, "max": 0.5572459101676941, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.0288543701172, "min": -27.058422088623047, "max": 156.0288543701172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005018020514398813, "min": -0.010089101269841194, "max": 0.21104928851127625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.405045747756958, "min": -2.713968276977539, "max": 50.65182876586914, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06539313033313697, "min": 0.06436432344378859, "max": 0.07502054994482696, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9808969549970546, "min": 0.47931415063568894, "max": 1.0580783874651316, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016923402143422413, "min": 0.0009923664614992305, "max": 0.016923402143422413, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2538510321513362, "min": 0.010916031076491535, "max": 0.2538510321513362, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4951975016333324e-06, "min": 7.4951975016333324e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011242796252449999, "min": 0.00011242796252449999, "max": 0.0032566961144346995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249836666666669, "min": 0.10249836666666669, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374755000000002, "min": 1.3886848, "max": 2.5275387, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002595868299999999, "min": 0.0002595868299999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038938024499999987, "min": 0.0038938024499999987, "max": 0.10857797347, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0073545570485293865, "min": 0.006939154118299484, "max": 0.37552642822265625, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11031835526227951, "min": 0.09714815765619278, "max": 2.6286849975585938, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.3010752688172, "min": 318.3010752688172, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29602.0, "min": 15984.0, "max": 33833.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6171612709920893, "min": -1.0000000521540642, "max": 1.6171612709920893, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.3959982022643, "min": -31.999601677060127, "max": 150.3959982022643, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6171612709920893, "min": -1.0000000521540642, "max": 1.6171612709920893, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.3959982022643, "min": -31.999601677060127, "max": 150.3959982022643, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024508718781421083, "min": 0.024508718781421083, "max": 7.8514409037306905, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2793108466721606, "min": 2.108992171521095, "max": 125.62305445969105, "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": "1682443652", "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 --force", "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": "1682446337" }, "total": 2685.616686757, "count": 1, "self": 0.43924392299959436, "children": { "run_training.setup": { "total": 0.09988479700041353, "count": 1, "self": 0.09988479700041353 }, "TrainerController.start_learning": { "total": 2685.077558037, "count": 1, "self": 1.92493240105523, "children": { "TrainerController._reset_env": { "total": 0.7986447540006338, "count": 1, "self": 0.7986447540006338 }, "TrainerController.advance": { "total": 2682.276490483944, "count": 63993, "self": 1.7712543108300451, "children": { "env_step": { "total": 1551.0266571381062, "count": 63993, "self": 1420.490764406848, "children": { "SubprocessEnvManager._take_step": { "total": 129.29176634126088, "count": 63993, "self": 4.558439135093067, "children": { "TorchPolicy.evaluate": { "total": 124.73332720616781, "count": 62572, "self": 124.73332720616781 } } }, "workers": { "total": 1.244126389997291, "count": 63993, "self": 0.0, "children": { "worker_root": { "total": 2679.9082534698955, "count": 63993, "is_parallel": true, "self": 1386.8890398986587, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003500740000163205, "count": 1, "is_parallel": true, "self": 0.0008780100006333669, "children": { "_process_rank_one_or_two_observation": { "total": 0.002622729999529838, "count": 8, "is_parallel": true, "self": 0.002622729999529838 } } }, "UnityEnvironment.step": { "total": 0.0600206689996412, "count": 1, "is_parallel": true, "self": 0.0006200999987413525, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005974599998808117, "count": 1, "is_parallel": true, "self": 0.0005974599998808117 }, "communicator.exchange": { "total": 0.056597319000502466, "count": 1, "is_parallel": true, "self": 0.056597319000502466 }, "steps_from_proto": { "total": 0.002205790000516572, "count": 1, "is_parallel": true, "self": 0.0005607299999610404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016450600005555316, "count": 8, "is_parallel": true, "self": 0.0016450600005555316 } } } } } } }, "UnityEnvironment.step": { "total": 1293.0192135712368, "count": 63992, "is_parallel": true, "self": 33.75553056911576, "children": { "UnityEnvironment._generate_step_input": { "total": 18.99033287214843, "count": 63992, "is_parallel": true, "self": 18.99033287214843 }, "communicator.exchange": { "total": 1144.8941080941486, "count": 63992, "is_parallel": true, "self": 1144.8941080941486 }, "steps_from_proto": { "total": 95.37924203582406, "count": 63992, "is_parallel": true, "self": 21.21593925208981, "children": { "_process_rank_one_or_two_observation": { "total": 74.16330278373425, "count": 511936, "is_parallel": true, "self": 74.16330278373425 } } } } } } } } } } }, "trainer_advance": { "total": 1129.478579035008, "count": 63993, "self": 3.9275680691807793, "children": { "process_trajectory": { "total": 125.2479259508309, "count": 63993, "self": 125.02865221383217, "children": { "RLTrainer._checkpoint": { "total": 0.21927373699872987, "count": 2, "self": 0.21927373699872987 } } }, "_update_policy": { "total": 1000.3030850149962, "count": 445, "self": 289.39026563901643, "children": { "TorchPPOOptimizer.update": { "total": 710.9128193759798, "count": 22815, "self": 710.9128193759798 } } } } } } }, "trainer_threads": { "total": 8.799997885944322e-07, "count": 1, "self": 8.799997885944322e-07 }, "TrainerController._save_models": { "total": 0.07748951800022041, "count": 1, "self": 0.0015975599999364931, "children": { "RLTrainer._checkpoint": { "total": 0.07589195800028392, "count": 1, "self": 0.07589195800028392 } } } } } } }