{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4366782307624817, "min": 0.42923325300216675, "max": 1.4561889171600342, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13205.1494140625, "min": 12794.5849609375, "max": 44174.9453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5029119253158569, "min": -0.09502245485782623, "max": 0.5029119253158569, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.80950927734375, "min": -22.805389404296875, "max": 139.80950927734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.12252424657344818, "min": -0.12252424657344818, "max": 0.3987865149974823, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -34.06174087524414, "min": -34.06174087524414, "max": 94.51240539550781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06464213442606186, "min": 0.06464213442606186, "max": 0.07322176946521115, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.904989881964866, "min": 0.48646363857852554, "max": 1.0618469534731727, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019030742706187688, "min": 8.226801563858261e-05, "max": 0.019030742706187688, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26643039788662765, "min": 0.001069484203301574, "max": 0.26643039788662765, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.70538314585715e-06, "min": 7.70538314585715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001078753640420001, "min": 0.0001078753640420001, "max": 0.0033819896726701997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256842857142856, "min": 0.10256842857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359579999999998, "min": 1.3691136000000002, "max": 2.5277543, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026658601428571446, "min": 0.00026658601428571446, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037322042000000025, "min": 0.0037322042000000025, "max": 0.11276024702000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01150902546942234, "min": 0.011050869710743427, "max": 0.49085602164268494, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16112636029720306, "min": 0.15471217036247253, "max": 3.4359922409057617, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.04651162790697, "min": 349.04651162790697, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30018.0, "min": 15984.0, "max": 32533.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.583551702742604, "min": -1.0000000521540642, "max": 1.583551702742604, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.76899813860655, "min": -32.000001668930054, "max": 137.76899813860655, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.583551702742604, "min": -1.0000000521540642, "max": 1.583551702742604, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.76899813860655, "min": -32.000001668930054, "max": 137.76899813860655, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04134875060502043, "min": 0.04134875060502043, "max": 10.692272217944264, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.597341302636778, "min": 3.5254722429963294, "max": 171.07635548710823, "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": "1784965992", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1784968263" }, "total": 2271.505002388, "count": 1, "self": 0.43686962499987203, "children": { "run_training.setup": { "total": 0.027244197000072745, "count": 1, "self": 0.027244197000072745 }, "TrainerController.start_learning": { "total": 2271.040888566, "count": 1, "self": 1.1980406879956718, "children": { "TrainerController._reset_env": { "total": 3.0380131940000865, "count": 1, "self": 3.0380131940000865 }, "TrainerController.advance": { "total": 2266.731462071004, "count": 63659, "self": 1.3089205210244472, "children": { "env_step": { "total": 1652.7078783429374, "count": 63659, "self": 1508.3596937849502, "children": { "SubprocessEnvManager._take_step": { "total": 143.6130775280269, "count": 63659, "self": 4.444954371985659, "children": { "TorchPolicy.evaluate": { "total": 139.16812315604125, "count": 62563, "self": 139.16812315604125 } } }, "workers": { "total": 0.735107029960318, "count": 63659, "self": 0.0, "children": { "worker_root": { "total": 2265.419830484971, "count": 63659, "is_parallel": true, "self": 868.7485369009441, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004442496999899959, "count": 1, "is_parallel": true, "self": 0.0031537080001271534, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012887889997728053, "count": 8, "is_parallel": true, "self": 0.0012887889997728053 } } }, "UnityEnvironment.step": { "total": 0.0544940460001726, "count": 1, "is_parallel": true, "self": 0.000594950000049721, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048237300006803707, "count": 1, "is_parallel": true, "self": 0.00048237300006803707 }, "communicator.exchange": { "total": 0.05185536299995874, "count": 1, "is_parallel": true, "self": 0.05185536299995874 }, "steps_from_proto": { "total": 0.0015613600000961014, "count": 1, "is_parallel": true, "self": 0.0003446440002790041, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012167159998170973, "count": 8, "is_parallel": true, "self": 0.0012167159998170973 } } } } } } }, "UnityEnvironment.step": { "total": 1396.671293584027, "count": 63658, "is_parallel": true, "self": 33.22733685303092, "children": { "UnityEnvironment._generate_step_input": { "total": 22.682657047029807, "count": 63658, "is_parallel": true, "self": 22.682657047029807 }, "communicator.exchange": { "total": 1235.3983705530143, "count": 63658, "is_parallel": true, "self": 1235.3983705530143 }, "steps_from_proto": { "total": 105.3629291309519, "count": 63658, "is_parallel": true, "self": 21.892577722033593, "children": { "_process_rank_one_or_two_observation": { "total": 83.4703514089183, "count": 509264, "is_parallel": true, "self": 83.4703514089183 } } } } } } } } } } }, "trainer_advance": { "total": 612.7146632070419, "count": 63659, "self": 2.280271530037453, "children": { "process_trajectory": { "total": 105.6782229039984, "count": 63659, "self": 105.46680828699823, "children": { "RLTrainer._checkpoint": { "total": 0.21141461700017317, "count": 2, "self": 0.21141461700017317 } } }, "_update_policy": { "total": 504.75616877300604, "count": 442, "self": 269.565082091005, "children": { "TorchPPOOptimizer.update": { "total": 235.191086682001, "count": 22818, "self": 235.191086682001 } } } } } } }, "trainer_threads": { "total": 9.40000063565094e-07, "count": 1, "self": 9.40000063565094e-07 }, "TrainerController._save_models": { "total": 0.0733716730001106, "count": 1, "self": 0.001036198000292643, "children": { "RLTrainer._checkpoint": { "total": 0.07233547499981796, "count": 1, "self": 0.07233547499981796 } } } } } } }