{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3003162145614624, "min": 0.2863345146179199, "max": 1.431641936302185, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9004.681640625, "min": 8631.267578125, "max": 43430.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29880.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29880.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6599324345588684, "min": -0.1303412765264511, "max": 0.6893135905265808, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 189.40060424804688, "min": -31.412246704101562, "max": 200.5902557373047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.055415306240320206, "min": 0.020324649289250374, "max": 0.5616396069526672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.904192924499512, "min": 5.772200584411621, "max": 133.10858154296875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06883770223323475, "min": 0.06599891154243577, "max": 0.07402100350276652, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9637278312652865, "min": 0.5033757686277118, "max": 1.0626234249017823, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015838802264635167, "min": 0.0013677447265551192, "max": 0.0163181629160092, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22174323170489232, "min": 0.013798443673784737, "max": 0.22992298533790745, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.512311781642861e-06, "min": 7.512311781642861e-06, "max": 0.000295236001588, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010517236494300006, "min": 0.00010517236494300006, "max": 0.0036331429889524, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250407142857142, "min": 0.10250407142857142, "max": 0.198412, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350569999999998, "min": 1.388884, "max": 2.6110476, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002601567357142859, "min": 0.0002601567357142859, "max": 0.0098413588, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003642194300000002, "min": 0.003642194300000002, "max": 0.12112365523999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.060732401907444, "min": 0.05396568030118942, "max": 0.7504539489746094, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.8502536416053772, "min": 0.7555195093154907, "max": 5.253177642822266, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 291.0769230769231, "min": 278.4, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30272.0, "min": 16679.0, "max": 32131.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7089230615932207, "min": -0.999987552408129, "max": 1.7089230615932207, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 177.72799840569496, "min": -31.999601677060127, "max": 185.5835978537798, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7089230615932207, "min": -0.999987552408129, "max": 1.7089230615932207, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 177.72799840569496, "min": -31.999601677060127, "max": 185.5835978537798, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.17768368658569392, "min": 0.15465896319312214, "max": 13.518103897571564, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 18.479103404912166, "min": 15.474371406860882, "max": 229.80776625871658, "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": "1699489735", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699492212" }, "total": 2477.698908709, "count": 1, "self": 0.490543969999635, "children": { "run_training.setup": { "total": 0.06510285000001659, "count": 1, "self": 0.06510285000001659 }, "TrainerController.start_learning": { "total": 2477.1432618890003, "count": 1, "self": 1.5751018350288177, "children": { "TrainerController._reset_env": { "total": 9.08778040499999, "count": 1, "self": 9.08778040499999 }, "TrainerController.advance": { "total": 2466.4038509389716, "count": 64276, "self": 1.6541504269539473, "children": { "env_step": { "total": 1809.6136070010234, "count": 64276, "self": 1663.5816875920682, "children": { "SubprocessEnvManager._take_step": { "total": 145.06840872898454, "count": 64276, "self": 4.954270600957557, "children": { "TorchPolicy.evaluate": { "total": 140.11413812802698, "count": 62559, "self": 140.11413812802698 } } }, "workers": { "total": 0.9635106799707387, "count": 64276, "self": 0.0, "children": { "worker_root": { "total": 2471.723682419055, "count": 64276, "is_parallel": true, "self": 940.274227079075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006545598999991853, "count": 1, "is_parallel": true, "self": 0.004649624000023778, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018959749999680753, "count": 8, "is_parallel": true, "self": 0.0018959749999680753 } } }, "UnityEnvironment.step": { "total": 0.07302987399998528, "count": 1, "is_parallel": true, "self": 0.0006421879999720659, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004616690000034396, "count": 1, "is_parallel": true, "self": 0.0004616690000034396 }, "communicator.exchange": { "total": 0.07015063500000451, "count": 1, "is_parallel": true, "self": 0.07015063500000451 }, "steps_from_proto": { "total": 0.0017753820000052656, "count": 1, "is_parallel": true, "self": 0.00036725500007150913, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014081269999337565, "count": 8, "is_parallel": true, "self": 0.0014081269999337565 } } } } } } }, "UnityEnvironment.step": { "total": 1531.44945533998, "count": 64275, "is_parallel": true, "self": 37.12061150493855, "children": { "UnityEnvironment._generate_step_input": { "total": 26.93049248903219, "count": 64275, "is_parallel": true, "self": 26.93049248903219 }, "communicator.exchange": { "total": 1357.4217102849998, "count": 64275, "is_parallel": true, "self": 1357.4217102849998 }, "steps_from_proto": { "total": 109.97664106100945, "count": 64275, "is_parallel": true, "self": 23.12036750991615, "children": { "_process_rank_one_or_two_observation": { "total": 86.8562735510933, "count": 514200, "is_parallel": true, "self": 86.8562735510933 } } } } } } } } } } }, "trainer_advance": { "total": 655.1360935109943, "count": 64276, "self": 3.060628591003592, "children": { "process_trajectory": { "total": 133.200598933991, "count": 64276, "self": 132.97541079699073, "children": { "RLTrainer._checkpoint": { "total": 0.2251881370002593, "count": 2, "self": 0.2251881370002593 } } }, "_update_policy": { "total": 518.8748659859998, "count": 453, "self": 307.7429137689981, "children": { "TorchPPOOptimizer.update": { "total": 211.1319522170017, "count": 22764, "self": 211.1319522170017 } } } } } } }, "trainer_threads": { "total": 1.056999735737918e-06, "count": 1, "self": 1.056999735737918e-06 }, "TrainerController._save_models": { "total": 0.07652765300008468, "count": 1, "self": 0.0013601529999505146, "children": { "RLTrainer._checkpoint": { "total": 0.07516750000013417, "count": 1, "self": 0.07516750000013417 } } } } } } }