{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48783212900161743, "min": 0.4809330403804779, "max": 1.4088127613067627, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14713.0166015625, "min": 14528.025390625, "max": 42737.7421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29954.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29954.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3786240518093109, "min": -0.09374184161424637, "max": 0.3786240518093109, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 99.95674896240234, "min": -22.4980411529541, "max": 99.95674896240234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014619356952607632, "min": -0.0008249550010077655, "max": 0.32800212502479553, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.8595101833343506, "min": -0.21531325578689575, "max": 78.72051239013672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06822947945260067, "min": 0.06489771259740965, "max": 0.07349181617724289, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9552127123364094, "min": 0.4817497198894451, "max": 1.045439059315957, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010695153003325686, "min": 0.0006909796061438143, "max": 0.011399863236551261, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1497321420465596, "min": 0.0096737144860134, "max": 0.15986601463459119, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.518076065435716e-06, "min": 7.518076065435716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010525306491610003, "min": 0.00010525306491610003, "max": 0.0035079428306857992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250599285714287, "min": 0.10250599285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350839000000002, "min": 1.3886848, "max": 2.5693142000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603486864285715, "min": 0.0002603486864285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003644881610000001, "min": 0.003644881610000001, "max": 0.11695448858000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011734756641089916, "min": 0.011646255850791931, "max": 0.4189160466194153, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16428659856319427, "min": 0.16304758191108704, "max": 2.9324123859405518, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 487.4754098360656, "min": 487.4754098360656, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29736.0, "min": 16753.0, "max": 32837.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.252190297529582, "min": -0.9999806972280625, "max": 1.252190297529582, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.63579844683409, "min": -30.99940161406994, "max": 77.63579844683409, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.252190297529582, "min": -0.9999806972280625, "max": 1.252190297529582, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.63579844683409, "min": -30.99940161406994, "max": 77.63579844683409, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05915487584500243, "min": 0.05915487584500243, "max": 7.5946758096380265, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6676023023901507, "min": 3.3404390568030067, "max": 129.10948876384646, "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": "1788702661", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788704966" }, "total": 2305.0791632019996, "count": 1, "self": 0.4791425659991546, "children": { "run_training.setup": { "total": 0.0288110719998258, "count": 1, "self": 0.0288110719998258 }, "TrainerController.start_learning": { "total": 2304.5712095640006, "count": 1, "self": 1.3243847240287323, "children": { "TrainerController._reset_env": { "total": 2.157245496000087, "count": 1, "self": 2.157245496000087 }, "TrainerController.advance": { "total": 2301.0036923229713, "count": 63454, "self": 1.3941105970220633, "children": { "env_step": { "total": 1672.2148914779605, "count": 63454, "self": 1516.6525901740001, "children": { "SubprocessEnvManager._take_step": { "total": 154.74295719802512, "count": 63454, "self": 4.642935758044132, "children": { "TorchPolicy.evaluate": { "total": 150.100021439981, "count": 62564, "self": 150.100021439981 } } }, "workers": { "total": 0.8193441059352153, "count": 63454, "self": 0.0, "children": { "worker_root": { "total": 2298.5768821619226, "count": 63454, "is_parallel": true, "self": 899.2950478037978, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018205340002168668, "count": 1, "is_parallel": true, "self": 0.0005613369999082352, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012591970003086317, "count": 8, "is_parallel": true, "self": 0.0012591970003086317 } } }, "UnityEnvironment.step": { "total": 0.055983178000133194, "count": 1, "is_parallel": true, "self": 0.0006176660003802681, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005141530000400962, "count": 1, "is_parallel": true, "self": 0.0005141530000400962 }, "communicator.exchange": { "total": 0.05299211200008358, "count": 1, "is_parallel": true, "self": 0.05299211200008358 }, "steps_from_proto": { "total": 0.0018592469996292493, "count": 1, "is_parallel": true, "self": 0.0003831099988929054, "children": { "_process_rank_one_or_two_observation": { "total": 0.001476137000736344, "count": 8, "is_parallel": true, "self": 0.001476137000736344 } } } } } } }, "UnityEnvironment.step": { "total": 1399.2818343581248, "count": 63453, "is_parallel": true, "self": 34.19844318621108, "children": { "UnityEnvironment._generate_step_input": { "total": 24.08182291593903, "count": 63453, "is_parallel": true, "self": 24.08182291593903 }, "communicator.exchange": { "total": 1230.437334018995, "count": 63453, "is_parallel": true, "self": 1230.437334018995 }, "steps_from_proto": { "total": 110.5642342369797, "count": 63453, "is_parallel": true, "self": 22.99906075076842, "children": { "_process_rank_one_or_two_observation": { "total": 87.56517348621128, "count": 507624, "is_parallel": true, "self": 87.56517348621128 } } } } } } } } } } }, "trainer_advance": { "total": 627.3946902479888, "count": 63454, "self": 2.6929361549173336, "children": { "process_trajectory": { "total": 109.9341929870684, "count": 63454, "self": 109.74110866706769, "children": { "RLTrainer._checkpoint": { "total": 0.19308432000070752, "count": 2, "self": 0.19308432000070752 } } }, "_update_policy": { "total": 514.7675611060031, "count": 450, "self": 275.2608939550014, "children": { "TorchPPOOptimizer.update": { "total": 239.5066671510017, "count": 22740, "self": 239.5066671510017 } } } } } } }, "trainer_threads": { "total": 8.990000424091704e-07, "count": 1, "self": 8.990000424091704e-07 }, "TrainerController._save_models": { "total": 0.0858861220003746, "count": 1, "self": 0.0010058050002044183, "children": { "RLTrainer._checkpoint": { "total": 0.08488031700017018, "count": 1, "self": 0.08488031700017018 } } } } } } }