{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6312389969825745, "min": 0.6312389969825745, "max": 1.4798674583435059, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 19017.96875, "min": 19017.96875, "max": 44893.2578125, "count": 16 }, "Pyramids.Step.mean": { "value": 479967.0, "min": 29952.0, "max": 479967.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479967.0, "min": 29952.0, "max": 479967.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04320937767624855, "min": -0.1650649756193161, "max": -0.04320937767624855, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -10.413459777832031, "min": -39.120399475097656, "max": -10.413459777832031, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023276491090655327, "min": 0.020585069432854652, "max": 0.3167571425437927, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.6096343994140625, "min": 4.9404168128967285, "max": 76.02171325683594, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06825308732089068, "min": 0.06565373146722542, "max": 0.07217240106241397, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9555432224924695, "min": 0.5023168953130257, "max": 0.9706860109822432, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0020275836428604145, "min": 0.00019976022404016454, "max": 0.011533955031952106, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.028386171000045802, "min": 0.0027966431365623037, "max": 0.08073768522366474, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.1136550097371428e-05, "min": 2.1136550097371428e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002959117013632, "min": 0.0002959117013632, "max": 0.0028478618507128003, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10704548571428571, "min": 0.10704548571428571, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4986367999999999, "min": 1.3382272, "max": 2.338055, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007138440228571429, "min": 0.0007138440228571429, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.00999381632, "min": 0.00999381632, "max": 0.09495379127999996, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01940550096333027, "min": 0.01940550096333027, "max": 0.537930428981781, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.27167701721191406, "min": 0.27167701721191406, "max": 3.7655131816864014, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 960.1212121212121, "min": 903.1851851851852, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31684.0, "min": 15984.0, "max": 32360.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.718303084147699, "min": -1.0000000521540642, "max": -0.4583059314857511, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -23.704001776874065, "min": -32.000001668930054, "max": -12.402401193976402, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.718303084147699, "min": -1.0000000521540642, "max": -0.4583059314857511, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -23.704001776874065, "min": -32.000001668930054, "max": -12.402401193976402, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1896194520434647, "min": 0.1896194520434647, "max": 12.725671171210706, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 6.257441917434335, "min": 6.257441917434335, "max": 203.6107387393713, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724864970", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 Training2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724866051" }, "total": 1081.515794761, "count": 1, "self": 0.47680288199990173, "children": { "run_training.setup": { "total": 0.05311954300009347, "count": 1, "self": 0.05311954300009347 }, "TrainerController.start_learning": { "total": 1080.985872336, "count": 1, "self": 0.6935020249838999, "children": { "TrainerController._reset_env": { "total": 1.72458831799986, "count": 1, "self": 1.72458831799986 }, "TrainerController.advance": { "total": 1078.479021980016, "count": 31544, "self": 0.6886810120017799, "children": { "env_step": { "total": 735.2812559690174, "count": 31544, "self": 656.4873832720507, "children": { "SubprocessEnvManager._take_step": { "total": 78.37407559397366, "count": 31544, "self": 2.413550496960397, "children": { "TorchPolicy.evaluate": { "total": 75.96052509701326, "count": 31319, "self": 75.96052509701326 } } }, "workers": { "total": 0.41979710299301587, "count": 31544, "self": 0.0, "children": { "worker_root": { "total": 1078.365320248991, "count": 31544, "is_parallel": true, "self": 482.2823866830049, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001966704999858848, "count": 1, "is_parallel": true, "self": 0.0005958489996373828, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013708560002214654, "count": 8, "is_parallel": true, "self": 0.0013708560002214654 } } }, "UnityEnvironment.step": { "total": 0.06317123899998478, "count": 1, "is_parallel": true, "self": 0.0006486729998869123, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005018510000809329, "count": 1, "is_parallel": true, "self": 0.0005018510000809329 }, "communicator.exchange": { "total": 0.06020810600011828, "count": 1, "is_parallel": true, "self": 0.06020810600011828 }, "steps_from_proto": { "total": 0.0018126089998986572, "count": 1, "is_parallel": true, "self": 0.00040580799941380974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014068010004848475, "count": 8, "is_parallel": true, "self": 0.0014068010004848475 } } } } } } }, "UnityEnvironment.step": { "total": 596.0829335659862, "count": 31543, "is_parallel": true, "self": 17.040681140945935, "children": { "UnityEnvironment._generate_step_input": { "total": 11.856495124032108, "count": 31543, "is_parallel": true, "self": 11.856495124032108 }, "communicator.exchange": { "total": 516.8297125670113, "count": 31543, "is_parallel": true, "self": 516.8297125670113 }, "steps_from_proto": { "total": 50.356044733996896, "count": 31543, "is_parallel": true, "self": 10.207620108108813, "children": { "_process_rank_one_or_two_observation": { "total": 40.14842462588808, "count": 252344, "is_parallel": true, "self": 40.14842462588808 } } } } } } } } } } }, "trainer_advance": { "total": 342.50908499899674, "count": 31544, "self": 1.1521001630271712, "children": { "process_trajectory": { "total": 64.55026601497048, "count": 31544, "self": 64.42133511197062, "children": { "RLTrainer._checkpoint": { "total": 0.12893090299985488, "count": 1, "self": 0.12893090299985488 } } }, "_update_policy": { "total": 276.8067188209991, "count": 209, "self": 156.66627787899415, "children": { "TorchPPOOptimizer.update": { "total": 120.14044094200494, "count": 11442, "self": 120.14044094200494 } } } } } } }, "trainer_threads": { "total": 9.25000222196104e-07, "count": 1, "self": 9.25000222196104e-07 }, "TrainerController._save_models": { "total": 0.08875908800018806, "count": 1, "self": 0.0013799280004604952, "children": { "RLTrainer._checkpoint": { "total": 0.08737915999972756, "count": 1, "self": 0.08737915999972756 } } } } } } }