{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3753083050251007, "min": 0.3742251396179199, "max": 1.4061357975006104, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11193.1953125, "min": 11193.1953125, "max": 42656.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5414407253265381, "min": -0.09649653732776642, "max": 0.5734546184539795, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.43763732910156, "min": -23.255664825439453, "max": 159.04246520996094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04994254186749458, "min": 0.007526482455432415, "max": 0.39979198575019836, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.784141540527344, "min": 2.054729700088501, "max": 94.75070190429688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06867265075765398, "min": 0.06426482251380618, "max": 0.0750999800949627, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9614171106071558, "min": 0.525699860664739, "max": 1.029808779704777, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01684641740280376, "min": 0.0001425578009271049, "max": 0.01700807027473096, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23584984363925268, "min": 0.0019958092129794686, "max": 0.2551210541209644, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.431183237257143e-06, "min": 7.431183237257143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001040365653216, "min": 0.0001040365653216, "max": 0.0032557725147426, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024770285714286, "min": 0.1024770285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346784000000004, "min": 1.3886848, "max": 2.4852574, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002574551542857143, "min": 0.0002574551542857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003604372160000001, "min": 0.003604372160000001, "max": 0.10855721425999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012062369845807552, "min": 0.012062369845807552, "max": 0.4544130861759186, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16887317597866058, "min": 0.16887317597866058, "max": 3.180891513824463, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 335.72340425531917, "min": 313.6875, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31558.0, "min": 15984.0, "max": 32709.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.559852612881284, "min": -1.0000000521540642, "max": 1.626896606904737, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.18599822372198, "min": -31.991601645946503, "max": 153.88359827548265, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.559852612881284, "min": -1.0000000521540642, "max": 1.626896606904737, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.18599822372198, "min": -31.991601645946503, "max": 153.88359827548265, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041910821603347644, "min": 0.04123519737368042, "max": 9.349706057459116, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9815280523180263, "min": 3.6257154021877795, "max": 149.59529691934586, "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": "1679208034", "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", "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": "1679210197" }, "total": 2163.0749941020003, "count": 1, "self": 0.576831370000491, "children": { "run_training.setup": { "total": 0.1444848619998993, "count": 1, "self": 0.1444848619998993 }, "TrainerController.start_learning": { "total": 2162.35367787, "count": 1, "self": 1.3523301169857405, "children": { "TrainerController._reset_env": { "total": 5.835542792000069, "count": 1, "self": 5.835542792000069 }, "TrainerController.advance": { "total": 2155.0730432870146, "count": 63849, "self": 1.493470893049107, "children": { "env_step": { "total": 1521.9090362130285, "count": 63849, "self": 1410.2034311710581, "children": { "SubprocessEnvManager._take_step": { "total": 110.87739392302524, "count": 63849, "self": 4.887321660017051, "children": { "TorchPolicy.evaluate": { "total": 105.99007226300819, "count": 62563, "self": 105.99007226300819 } } }, "workers": { "total": 0.8282111189450916, "count": 63849, "self": 0.0, "children": { "worker_root": { "total": 2157.242933940994, "count": 63849, "is_parallel": true, "self": 865.6832500049666, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019050760001846356, "count": 1, "is_parallel": true, "self": 0.0006332310003926978, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012718449997919379, "count": 8, "is_parallel": true, "self": 0.0012718449997919379 } } }, "UnityEnvironment.step": { "total": 0.07155778499986809, "count": 1, "is_parallel": true, "self": 0.0005572069997015205, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004888040000423644, "count": 1, "is_parallel": true, "self": 0.0004888040000423644 }, "communicator.exchange": { "total": 0.06875574700006837, "count": 1, "is_parallel": true, "self": 0.06875574700006837 }, "steps_from_proto": { "total": 0.0017560270000558376, "count": 1, "is_parallel": true, "self": 0.00042490600003475265, "children": { "_process_rank_one_or_two_observation": { "total": 0.001331121000021085, "count": 8, "is_parallel": true, "self": 0.001331121000021085 } } } } } } }, "UnityEnvironment.step": { "total": 1291.5596839360276, "count": 63848, "is_parallel": true, "self": 31.154320796015554, "children": { "UnityEnvironment._generate_step_input": { "total": 23.82151703499403, "count": 63848, "is_parallel": true, "self": 23.82151703499403 }, "communicator.exchange": { "total": 1140.9575612299914, "count": 63848, "is_parallel": true, "self": 1140.9575612299914 }, "steps_from_proto": { "total": 95.62628487502661, "count": 63848, "is_parallel": true, "self": 20.4890751201242, "children": { "_process_rank_one_or_two_observation": { "total": 75.13720975490241, "count": 510784, "is_parallel": true, "self": 75.13720975490241 } } } } } } } } } } }, "trainer_advance": { "total": 631.6705361809372, "count": 63849, "self": 2.513996289980014, "children": { "process_trajectory": { "total": 121.47925874595103, "count": 63849, "self": 121.26979283495075, "children": { "RLTrainer._checkpoint": { "total": 0.20946591100027945, "count": 2, "self": 0.20946591100027945 } } }, "_update_policy": { "total": 507.6772811450062, "count": 443, "self": 323.41075435101516, "children": { "TorchPPOOptimizer.update": { "total": 184.26652679399103, "count": 22869, "self": 184.26652679399103 } } } } } } }, "trainer_threads": { "total": 8.389997674385086e-07, "count": 1, "self": 8.389997674385086e-07 }, "TrainerController._save_models": { "total": 0.09276083499980814, "count": 1, "self": 0.0013950509996902838, "children": { "RLTrainer._checkpoint": { "total": 0.09136578400011786, "count": 1, "self": 0.09136578400011786 } } } } } } }