{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15615423023700714, "min": 0.13672760128974915, "max": 0.34243956208229065, "count": 67 }, "Pyramids.Policy.Entropy.sum": { "value": 4734.59619140625, "min": 4101.828125, "max": 10338.935546875, "count": 67 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 236.61417322834646, "min": 208.83098591549296, "max": 328.8679245283019, "count": 67 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30050.0, "min": 17430.0, "max": 32475.0, "count": 67 }, "Pyramids.Step.mean": { "value": 2999968.0, "min": 1019952.0, "max": 2999968.0, "count": 67 }, "Pyramids.Step.sum": { "value": 2999968.0, "min": 1019952.0, "max": 2999968.0, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.816567063331604, "min": 0.5839594602584839, "max": 0.8987612128257751, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.703857421875, "min": 107.44853973388672, "max": 275.02093505859375, "count": 67 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01298210583627224, "min": -0.01796101965010166, "max": 0.03628607466816902, "count": 67 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.842703342437744, "min": -5.011124610900879, "max": 10.704391479492188, "count": 67 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7167281115544029, "min": 1.5956226278026149, "max": 1.784820128580649, "count": 67 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 219.74119827896357, "min": 84.56799927353859, "max": 252.34579864144325, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7167281115544029, "min": 1.5956226278026149, "max": 1.784820128580649, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 219.74119827896357, "min": 84.56799927353859, "max": 252.34579864144325, "count": 67 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01805530026851443, "min": 0.017222659088590046, "max": 0.0430784829593492, "count": 67 }, "Pyramids.Policy.RndReward.sum": { "value": 2.311078434369847, "min": 2.2831595968455076, "max": 3.8164102025912143, "count": 67 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07058840989797502, "min": 0.06393769389279781, "max": 0.07210166715257973, "count": 67 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9882377385716503, "min": 0.6489150043732176, "max": 1.0689797951296593, "count": 67 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014445648861209946, "min": 0.012515812667078097, "max": 0.01652194130708397, "count": 67 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20223908405693924, "min": 0.11264231400370288, "max": 0.2432429228342074, "count": 67 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4657566543047613e-06, "min": 1.4657566543047613e-06, "max": 0.00019895765590301478, "count": 67 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.052059316026666e-05, "min": 2.052059316026666e-05, "max": 0.002857728747423934, "count": 67 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048855238095236, "min": 0.10048855238095236, "max": 0.1663192074074074, "count": 67 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068397333333331, "min": 1.4068397333333331, "max": 2.452576066666667, "count": 67 }, "Pyramids.Policy.Beta.mean": { "value": 5.8806382857142845e-05, "min": 5.8806382857142845e-05, "max": 0.00663528882, "count": 67 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008232893599999998, "min": 0.0008232893599999998, "max": 0.09531234906000001, "count": 67 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00735260546207428, "min": 0.00735260546207428, "max": 0.012687886133790016, "count": 67 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10293647646903992, "min": 0.10293647646903992, "max": 0.1796223223209381, "count": 67 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740463837", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740468685" }, "total": 4848.4699701360005, "count": 1, "self": 0.6253432369994698, "children": { "run_training.setup": { "total": 0.02189098400003786, "count": 1, "self": 0.02189098400003786 }, "TrainerController.start_learning": { "total": 4847.8227359150005, "count": 1, "self": 2.4374058329813124, "children": { "TrainerController._reset_env": { "total": 2.2221810120004193, "count": 1, "self": 2.2221810120004193 }, "TrainerController.advance": { "total": 4843.0703028380185, "count": 131437, "self": 2.661997735350269, "children": { "env_step": { "total": 3495.2743252788623, "count": 131437, "self": 3206.481996685923, "children": { "SubprocessEnvManager._take_step": { "total": 287.3366313968613, "count": 131437, "self": 8.623035777674431, "children": { "TorchPolicy.evaluate": { "total": 278.7135956191869, "count": 125084, "self": 278.7135956191869 } } }, "workers": { "total": 1.4556971960778355, "count": 131437, "self": 0.0, "children": { "worker_root": { "total": 4838.427060180207, "count": 131437, "is_parallel": true, "self": 1842.6370994911567, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002033137000125862, "count": 1, "is_parallel": true, "self": 0.0006336760011436127, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013994609989822493, "count": 8, "is_parallel": true, "self": 0.0013994609989822493 } } }, "UnityEnvironment.step": { "total": 0.04776940400006424, "count": 1, "is_parallel": true, "self": 0.0005074149994470645, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045858600014980766, "count": 1, "is_parallel": true, "self": 0.00045858600014980766 }, "communicator.exchange": { "total": 0.04517834300031609, "count": 1, "is_parallel": true, "self": 0.04517834300031609 }, "steps_from_proto": { "total": 0.0016250600001512794, "count": 1, "is_parallel": true, "self": 0.0003524390012898948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012726209988613846, "count": 8, "is_parallel": true, "self": 0.0012726209988613846 } } } } } } }, "UnityEnvironment.step": { "total": 2995.7899606890505, "count": 131436, "is_parallel": true, "self": 61.53508040731049, "children": { "UnityEnvironment._generate_step_input": { "total": 46.23826532296016, "count": 131436, "is_parallel": true, "self": 46.23826532296016 }, "communicator.exchange": { "total": 2703.79442924589, "count": 131436, "is_parallel": true, "self": 2703.79442924589 }, "steps_from_proto": { "total": 184.22218571288977, "count": 131436, "is_parallel": true, "self": 36.02774608961863, "children": { "_process_rank_one_or_two_observation": { "total": 148.19443962327114, "count": 1051488, "is_parallel": true, "self": 148.19443962327114 } } } } } } } } } } }, "trainer_advance": { "total": 1345.1339798238055, "count": 131437, "self": 5.093404834877219, "children": { "process_trajectory": { "total": 255.96369967491592, "count": 131437, "self": 255.42970659591674, "children": { "RLTrainer._checkpoint": { "total": 0.533993078999174, "count": 5, "self": 0.533993078999174 } } }, "_update_policy": { "total": 1084.0768753140123, "count": 948, "self": 596.9266287098235, "children": { "TorchPPOOptimizer.update": { "total": 487.15024660418885, "count": 45582, "self": 487.15024660418885 } } } } } } }, "trainer_threads": { "total": 9.840005077421665e-07, "count": 1, "self": 9.840005077421665e-07 }, "TrainerController._save_models": { "total": 0.09284524800023064, "count": 1, "self": 0.001403803000357584, "children": { "RLTrainer._checkpoint": { "total": 0.09144144499987306, "count": 1, "self": 0.09144144499987306 } } } } } } }