{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41704049706459045, "min": 0.41002610325813293, "max": 1.4648184776306152, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12531.232421875, "min": 12097.41015625, "max": 44436.734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.596138060092926, "min": -0.11757717281579971, "max": 0.6042474508285522, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.7070770263672, "min": -28.218521118164062, "max": 169.1892852783203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07390497624874115, "min": -0.006074411794543266, "max": 0.35640329122543335, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 20.91510772705078, "min": -1.6461656093597412, "max": 84.46758270263672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06840651527108137, "min": 0.06483729437154363, "max": 0.07449178403753433, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9576912137951392, "min": 0.4917558679630145, "max": 1.0574620285364755, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017522719688367074, "min": 0.00015051816314984014, "max": 0.018688217902599107, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24531807563713906, "min": 0.0016556997946482416, "max": 0.2651820292715759, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.361711831842859e-06, "min": 7.361711831842859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010306396564580003, "min": 0.00010306396564580003, "max": 0.0035090015303329, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245387142857144, "min": 0.10245387142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343542000000002, "min": 1.3691136000000002, "max": 2.5696671, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025514175571428576, "min": 0.00025514175571428576, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035719845800000006, "min": 0.0035719845800000006, "max": 0.11698974329000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013458915054798126, "min": 0.013458915054798126, "max": 0.4578872323036194, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18842481076717377, "min": 0.18842481076717377, "max": 3.2052106857299805, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 314.4791666666667, "min": 300.1979166666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30190.0, "min": 15984.0, "max": 32093.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6438499811726313, "min": -1.0000000521540642, "max": 1.6778679422093827, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 157.8095981925726, "min": -32.000001668930054, "max": 172.8203980475664, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6438499811726313, "min": -1.0000000521540642, "max": 1.6778679422093827, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 157.8095981925726, "min": -32.000001668930054, "max": 172.8203980475664, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04385424695798671, "min": 0.04269222809748896, "max": 8.888745879754424, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.210007707966724, "min": 4.210007707966724, "max": 142.21993407607079, "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": "1715672731", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715674976" }, "total": 2244.839601249, "count": 1, "self": 0.7459130830002323, "children": { "run_training.setup": { "total": 0.04923896800005423, "count": 1, "self": 0.04923896800005423 }, "TrainerController.start_learning": { "total": 2244.044449198, "count": 1, "self": 1.3705190190235044, "children": { "TrainerController._reset_env": { "total": 2.178777944000103, "count": 1, "self": 2.178777944000103 }, "TrainerController.advance": { "total": 2240.3666258679764, "count": 63955, "self": 1.4858646750253683, "children": { "env_step": { "total": 1604.0709354750122, "count": 63955, "self": 1472.8144537790472, "children": { "SubprocessEnvManager._take_step": { "total": 130.40933459698135, "count": 63955, "self": 4.6102120589632705, "children": { "TorchPolicy.evaluate": { "total": 125.79912253801808, "count": 62579, "self": 125.79912253801808 } } }, "workers": { "total": 0.8471470989836689, "count": 63955, "self": 0.0, "children": { "worker_root": { "total": 2239.021191920028, "count": 63955, "is_parallel": true, "self": 891.2746604730173, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00204140699997879, "count": 1, "is_parallel": true, "self": 0.0005854059998000594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014560010001787305, "count": 8, "is_parallel": true, "self": 0.0014560010001787305 } } }, "UnityEnvironment.step": { "total": 0.04848448500001723, "count": 1, "is_parallel": true, "self": 0.0006518759998925816, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004389240000364225, "count": 1, "is_parallel": true, "self": 0.0004389240000364225 }, "communicator.exchange": { "total": 0.04569351400004962, "count": 1, "is_parallel": true, "self": 0.04569351400004962 }, "steps_from_proto": { "total": 0.0017001710000386083, "count": 1, "is_parallel": true, "self": 0.00034697000000960543, "children": { "_process_rank_one_or_two_observation": { "total": 0.001353201000029003, "count": 8, "is_parallel": true, "self": 0.001353201000029003 } } } } } } }, "UnityEnvironment.step": { "total": 1347.7465314470105, "count": 63954, "is_parallel": true, "self": 34.08612006289445, "children": { "UnityEnvironment._generate_step_input": { "total": 23.81108018600753, "count": 63954, "is_parallel": true, "self": 23.81108018600753 }, "communicator.exchange": { "total": 1192.725198912039, "count": 63954, "is_parallel": true, "self": 1192.725198912039 }, "steps_from_proto": { "total": 97.12413228606943, "count": 63954, "is_parallel": true, "self": 19.61563785514045, "children": { "_process_rank_one_or_two_observation": { "total": 77.50849443092898, "count": 511632, "is_parallel": true, "self": 77.50849443092898 } } } } } } } } } } }, "trainer_advance": { "total": 634.8098257179388, "count": 63955, "self": 2.659910132915911, "children": { "process_trajectory": { "total": 127.05026433102717, "count": 63955, "self": 126.60175092002714, "children": { "RLTrainer._checkpoint": { "total": 0.44851341100002173, "count": 2, "self": 0.44851341100002173 } } }, "_update_policy": { "total": 505.0996512539957, "count": 448, "self": 298.9264912089643, "children": { "TorchPPOOptimizer.update": { "total": 206.1731600450314, "count": 22797, "self": 206.1731600450314 } } } } } } }, "trainer_threads": { "total": 1.4349998309626244e-06, "count": 1, "self": 1.4349998309626244e-06 }, "TrainerController._save_models": { "total": 0.12852493200034587, "count": 1, "self": 0.0021049900005891686, "children": { "RLTrainer._checkpoint": { "total": 0.1264199419997567, "count": 1, "self": 0.1264199419997567 } } } } } } }