{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13125251233577728, "min": 0.1266728788614273, "max": 1.4334834814071655, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3937.575439453125, "min": 3788.02587890625, "max": 43486.15625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999971.0, "min": 29952.0, "max": 2999971.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999971.0, "min": 29952.0, "max": 2999971.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7409255504608154, "min": -0.10395684093236923, "max": 0.8428269028663635, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 214.868408203125, "min": -24.949642181396484, "max": 255.37655639648438, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014302385039627552, "min": -0.08000713586807251, "max": 0.3142332434654236, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.14769172668457, "min": -20.641841888427734, "max": 75.73020935058594, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06710547671814095, "min": 0.0634419109643906, "max": 0.07480556164908611, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9394766740539732, "min": 0.4866420462852659, "max": 1.0744367132702952, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01554489962013793, "min": 0.0006077335625649556, "max": 0.01744368394845099, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21762859468193102, "min": 0.008330488975790263, "max": 0.2610343461856246, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4382138063428581e-06, "min": 1.4382138063428581e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0134993288800014e-05, "min": 2.0134993288800014e-05, "max": 0.003969560076813332, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047937142857145, "min": 0.10047937142857145, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067112000000004, "min": 1.3962282666666668, "max": 2.737505266666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.788920571428576e-05, "min": 5.788920571428576e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008104488800000007, "min": 0.0008104488800000007, "max": 0.13232634799999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006704431492835283, "min": 0.006704431492835283, "max": 0.48235660791397095, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09386204183101654, "min": 0.09386204183101654, "max": 3.3764963150024414, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 250.67241379310346, "min": 210.52482269503545, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29078.0, "min": 15984.0, "max": 32958.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.697591361043782, "min": -1.0000000521540642, "max": 1.7752850921230112, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 196.92059788107872, "min": -30.433601640164852, "max": 250.3151979893446, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.697591361043782, "min": -1.0000000521540642, "max": 1.7752850921230112, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 196.92059788107872, "min": -30.433601640164852, "max": 250.3151979893446, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017440856715626885, "min": 0.01581837089132874, "max": 9.29213576670736, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0231393790127186, "min": 1.9819676644983701, "max": 148.67417226731777, "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": "1706728531", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706736123" }, "total": 7591.881738983, "count": 1, "self": 0.5082409179995011, "children": { "run_training.setup": { "total": 0.051130151999586815, "count": 1, "self": 0.051130151999586815 }, "TrainerController.start_learning": { "total": 7591.322367913001, "count": 1, "self": 4.580546740238788, "children": { "TrainerController._reset_env": { "total": 3.188782046000142, "count": 1, "self": 3.188782046000142 }, "TrainerController.advance": { "total": 7583.460988532762, "count": 194613, "self": 4.724775389248862, "children": { "env_step": { "total": 5582.194257566906, "count": 194613, "self": 5157.444570339441, "children": { "SubprocessEnvManager._take_step": { "total": 421.9881304117371, "count": 194613, "self": 15.415391997128609, "children": { "TorchPolicy.evaluate": { "total": 406.57273841460847, "count": 187563, "self": 406.57273841460847 } } }, "workers": { "total": 2.7615568157279995, "count": 194613, "self": 0.0, "children": { "worker_root": { "total": 7574.286593487962, "count": 194613, "is_parallel": true, "self": 2808.250156997893, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005371056000058161, "count": 1, "is_parallel": true, "self": 0.003946133999306767, "children": { "_process_rank_one_or_two_observation": { "total": 0.001424922000751394, "count": 8, "is_parallel": true, "self": 0.001424922000751394 } } }, "UnityEnvironment.step": { "total": 0.053897405000043364, "count": 1, "is_parallel": true, "self": 0.0006992150001678965, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005338639998626604, "count": 1, "is_parallel": true, "self": 0.0005338639998626604 }, "communicator.exchange": { "total": 0.050768492000315746, "count": 1, "is_parallel": true, "self": 0.050768492000315746 }, "steps_from_proto": { "total": 0.0018958339996970608, "count": 1, "is_parallel": true, "self": 0.00040937699895948754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014864570007375733, "count": 8, "is_parallel": true, "self": 0.0014864570007375733 } } } } } } }, "UnityEnvironment.step": { "total": 4766.036436490069, "count": 194612, "is_parallel": true, "self": 111.07986765572969, "children": { "UnityEnvironment._generate_step_input": { "total": 78.7007358669689, "count": 194612, "is_parallel": true, "self": 78.7007358669689 }, "communicator.exchange": { "total": 4250.520715371329, "count": 194612, "is_parallel": true, "self": 4250.520715371329 }, "steps_from_proto": { "total": 325.73511759604116, "count": 194612, "is_parallel": true, "self": 67.39921052791487, "children": { "_process_rank_one_or_two_observation": { "total": 258.3359070681263, "count": 1556896, "is_parallel": true, "self": 258.3359070681263 } } } } } } } } } } }, "trainer_advance": { "total": 1996.5419555766066, "count": 194613, "self": 9.159311783740577, "children": { "process_trajectory": { "total": 416.15789446488, "count": 194613, "self": 415.5295719828782, "children": { "RLTrainer._checkpoint": { "total": 0.6283224820017494, "count": 6, "self": 0.6283224820017494 } } }, "_update_policy": { "total": 1571.224749327986, "count": 1398, "self": 930.3179039760244, "children": { "TorchPPOOptimizer.update": { "total": 640.9068453519617, "count": 68412, "self": 640.9068453519617 } } } } } } }, "trainer_threads": { "total": 1.0040002962341532e-06, "count": 1, "self": 1.0040002962341532e-06 }, "TrainerController._save_models": { "total": 0.09204958999907831, "count": 1, "self": 0.001677372998528881, "children": { "RLTrainer._checkpoint": { "total": 0.09037221700054943, "count": 1, "self": 0.09037221700054943 } } } } } } }