{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15044279396533966, "min": 0.13375379145145416, "max": 1.4381340742111206, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4532.54052734375, "min": 4063.975341796875, "max": 43627.234375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999898.0, "min": 29952.0, "max": 2999898.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999898.0, "min": 29952.0, "max": 2999898.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7566414475440979, "min": -0.1753283441066742, "max": 0.8517789840698242, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 227.7490692138672, "min": -41.552818298339844, "max": 253.83013916015625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002145596081390977, "min": -0.007263427600264549, "max": 0.31291162967681885, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6458244323730469, "min": -2.157238006591797, "max": 74.1600570678711, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06360184082709068, "min": 0.06360184082709068, "max": 0.07332028726592572, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8904257715792696, "min": 0.47079630343570655, "max": 1.0624053268887412, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017139451402454396, "min": 0.000837558993595087, "max": 0.017827829675211217, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23995231963436156, "min": 0.011725825910331219, "max": 0.24958961545295702, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.459492370678568e-06, "min": 1.459492370678568e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0432893189499952e-05, "min": 2.0432893189499952e-05, "max": 0.004011360562879832, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004864642857143, "min": 0.1004864642857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068105000000002, "min": 1.3962282666666668, "max": 2.782468866666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.8597782142857054e-05, "min": 5.8597782142857054e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008203689499999987, "min": 0.0008203689499999987, "max": 0.13371830465, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005334161687642336, "min": 0.005208165850490332, "max": 0.3993033766746521, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07467826455831528, "min": 0.07291432470083237, "max": 2.79512357711792, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 234.98461538461538, "min": 214.96268656716418, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30548.0, "min": 15984.0, "max": 34306.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.734077508481898, "min": -1.0000000521540642, "max": 1.7701074513259218, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 223.69599859416485, "min": -27.984401658177376, "max": 237.19439847767353, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.734077508481898, "min": -1.0000000521540642, "max": 1.7701074513259218, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 223.69599859416485, "min": -27.984401658177376, "max": 237.19439847767353, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0128767684406859, "min": 0.012593642679577762, "max": 7.484875182621181, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.661103128848481, "min": 1.5345477966766339, "max": 119.7580029219389, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752340452", "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": "1752350971" }, "total": 10519.730625836, "count": 1, "self": 0.7588883980006358, "children": { "run_training.setup": { "total": 0.03093724299992573, "count": 1, "self": 0.03093724299992573 }, "TrainerController.start_learning": { "total": 10518.940800195, "count": 1, "self": 6.9295339211967075, "children": { "TrainerController._reset_env": { "total": 4.348806910999883, "count": 1, "self": 4.348806910999883 }, "TrainerController.advance": { "total": 10507.566589916805, "count": 194719, "self": 7.871507933679823, "children": { "env_step": { "total": 7379.331895034259, "count": 194719, "self": 6911.956747127414, "children": { "SubprocessEnvManager._take_step": { "total": 463.32433933604216, "count": 194719, "self": 20.951257697458686, "children": { "TorchPolicy.evaluate": { "total": 442.37308163858347, "count": 187560, "self": 442.37308163858347 } } }, "workers": { "total": 4.050808570802701, "count": 194719, "self": 0.0, "children": { "worker_root": { "total": 10490.406852881766, "count": 194719, "is_parallel": true, "self": 4119.923671542867, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007261976000108916, "count": 1, "is_parallel": true, "self": 0.004448279999905935, "children": { "_process_rank_one_or_two_observation": { "total": 0.002813696000202981, "count": 8, "is_parallel": true, "self": 0.002813696000202981 } } }, "UnityEnvironment.step": { "total": 0.06011857099997542, "count": 1, "is_parallel": true, "self": 0.0006970870001623553, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00064267499988091, "count": 1, "is_parallel": true, "self": 0.00064267499988091 }, "communicator.exchange": { "total": 0.0566563639999913, "count": 1, "is_parallel": true, "self": 0.0566563639999913 }, "steps_from_proto": { "total": 0.0021224449999408534, "count": 1, "is_parallel": true, "self": 0.0004974770004082529, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016249679995326005, "count": 8, "is_parallel": true, "self": 0.0016249679995326005 } } } } } } }, "UnityEnvironment.step": { "total": 6370.483181338899, "count": 194718, "is_parallel": true, "self": 142.92265311580832, "children": { "UnityEnvironment._generate_step_input": { "total": 92.92594240906715, "count": 194718, "is_parallel": true, "self": 92.92594240906715 }, "communicator.exchange": { "total": 5745.828472469098, "count": 194718, "is_parallel": true, "self": 5745.828472469098 }, "steps_from_proto": { "total": 388.8061133449255, "count": 194718, "is_parallel": true, "self": 84.59424011886654, "children": { "_process_rank_one_or_two_observation": { "total": 304.21187322605897, "count": 1557744, "is_parallel": true, "self": 304.21187322605897 } } } } } } } } } } }, "trainer_advance": { "total": 3120.363186948867, "count": 194719, "self": 13.49916869363733, "children": { "process_trajectory": { "total": 486.79231573420634, "count": 194719, "self": 486.0928895862064, "children": { "RLTrainer._checkpoint": { "total": 0.6994261479999295, "count": 6, "self": 0.6994261479999295 } } }, "_update_policy": { "total": 2620.071702521024, "count": 1407, "self": 1052.8617581508422, "children": { "TorchPPOOptimizer.update": { "total": 1567.2099443701816, "count": 68400, "self": 1567.2099443701816 } } } } } } }, "trainer_threads": { "total": 1.155998688773252e-06, "count": 1, "self": 1.155998688773252e-06 }, "TrainerController._save_models": { "total": 0.09586828999999852, "count": 1, "self": 0.00237369100068463, "children": { "RLTrainer._checkpoint": { "total": 0.0934945989993139, "count": 1, "self": 0.0934945989993139 } } } } } } }