{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8140870332717896, "min": 0.8140870332717896, "max": 1.3965567350387573, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 24500.763671875, "min": 24500.763671875, "max": 42365.9453125, "count": 16 }, "Pyramids.Step.mean": { "value": 479948.0, "min": 29952.0, "max": 479948.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479948.0, "min": 29952.0, "max": 479948.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09889139980077744, "min": -0.0866457149386406, "max": 0.09889139980077744, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 24.525066375732422, "min": -20.794971466064453, "max": 24.525066375732422, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013121883384883404, "min": 0.013121883384883404, "max": 0.5604943633079529, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2542271614074707, "min": 3.2542271614074707, "max": 132.837158203125, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07320434617189886, "min": 0.06461985435301723, "max": 0.0736342190077105, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.024860846406584, "min": 0.5154395330539735, "max": 1.024860846406584, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008114452609998891, "min": 0.0007525435187473575, "max": 0.009662751753405488, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11360233653998449, "min": 0.00903052222496829, "max": 0.11360233653998449, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0494550311371424e-05, "min": 2.0494550311371424e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00028692370435919994, "min": 0.00028692370435919994, "max": 0.0027993037668988, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10683148571428572, "min": 0.10683148571428572, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4956408, "min": 1.3773696000000002, "max": 2.2553123999999998, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0006924654228571428, "min": 0.0006924654228571428, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.009694515919999999, "min": 0.009694515919999999, "max": 0.09332680988000003, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.021623099222779274, "min": 0.021623099222779274, "max": 0.5177385210990906, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.30272337794303894, "min": 0.30272337794303894, "max": 3.6241695880889893, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 776.3, "min": 775.921052631579, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31052.0, "min": 15984.0, "max": 33583.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.4234449589625001, "min": -1.0000000521540642, "max": 0.4234449589625001, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 16.937798358500004, "min": -29.947601668536663, "max": 16.937798358500004, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.4234449589625001, "min": -1.0000000521540642, "max": 0.4234449589625001, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 16.937798358500004, "min": -29.947601668536663, "max": 16.937798358500004, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.17633211204665714, "min": 0.17633211204665714, "max": 10.779729153960943, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 7.053284481866285, "min": 6.714518571272492, "max": 172.4756664633751, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691073002", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn --force ./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": "1691073874" }, "total": 871.4434206169999, "count": 1, "self": 0.32518954499937536, "children": { "run_training.setup": { "total": 0.04896397800075647, "count": 1, "self": 0.04896397800075647 }, "TrainerController.start_learning": { "total": 871.0692670939998, "count": 1, "self": 0.7495274820303166, "children": { "TrainerController._reset_env": { "total": 4.376205507999657, "count": 1, "self": 4.376205507999657 }, "TrainerController.advance": { "total": 865.8476183079702, "count": 31605, "self": 0.7288256318506683, "children": { "env_step": { "total": 568.7123238700296, "count": 31605, "self": 512.6138779881412, "children": { "SubprocessEnvManager._take_step": { "total": 55.648934751046, "count": 31605, "self": 2.361382144156778, "children": { "TorchPolicy.evaluate": { "total": 53.28755260688922, "count": 31316, "self": 53.28755260688922 } } }, "workers": { "total": 0.44951113084243843, "count": 31605, "self": 0.0, "children": { "worker_root": { "total": 869.6091956549708, "count": 31605, "is_parallel": true, "self": 408.4841973718785, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001994140000533662, "count": 1, "is_parallel": true, "self": 0.0005668380008501117, "children": { "_process_rank_one_or_two_observation": { "total": 0.00142730199968355, "count": 8, "is_parallel": true, "self": 0.00142730199968355 } } }, "UnityEnvironment.step": { "total": 0.0463572299995576, "count": 1, "is_parallel": true, "self": 0.0003554879995135707, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000373339999896416, "count": 1, "is_parallel": true, "self": 0.000373339999896416 }, "communicator.exchange": { "total": 0.0444114140000238, "count": 1, "is_parallel": true, "self": 0.0444114140000238 }, "steps_from_proto": { "total": 0.0012169880001238198, "count": 1, "is_parallel": true, "self": 0.0003044640006919508, "children": { "_process_rank_one_or_two_observation": { "total": 0.000912523999431869, "count": 8, "is_parallel": true, "self": 0.000912523999431869 } } } } } } }, "UnityEnvironment.step": { "total": 461.1249982830923, "count": 31604, "is_parallel": true, "self": 12.554558846159125, "children": { "UnityEnvironment._generate_step_input": { "total": 8.828483802870323, "count": 31604, "is_parallel": true, "self": 8.828483802870323 }, "communicator.exchange": { "total": 402.5129727841095, "count": 31604, "is_parallel": true, "self": 402.5129727841095 }, "steps_from_proto": { "total": 37.228982849953354, "count": 31604, "is_parallel": true, "self": 7.719658702796551, "children": { "_process_rank_one_or_two_observation": { "total": 29.509324147156804, "count": 252832, "is_parallel": true, "self": 29.509324147156804 } } } } } } } } } } }, "trainer_advance": { "total": 296.40646880608983, "count": 31605, "self": 1.2728012682000553, "children": { "process_trajectory": { "total": 49.30109030289077, "count": 31605, "self": 49.18668687889112, "children": { "RLTrainer._checkpoint": { "total": 0.1144034239996472, "count": 1, "self": 0.1144034239996472 } } }, "_update_policy": { "total": 245.832577234999, "count": 212, "self": 155.21310404001815, "children": { "TorchPPOOptimizer.update": { "total": 90.61947319498086, "count": 11424, "self": 90.61947319498086 } } } } } } }, "trainer_threads": { "total": 9.609993867343292e-07, "count": 1, "self": 9.609993867343292e-07 }, "TrainerController._save_models": { "total": 0.09591483500025788, "count": 1, "self": 0.0013531670001611928, "children": { "RLTrainer._checkpoint": { "total": 0.09456166800009669, "count": 1, "self": 0.09456166800009669 } } } } } } }