{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21305184066295624, "min": 0.21279378235340118, "max": 1.406337857246399, "count": 74 }, "Pyramids.Policy.Entropy.sum": { "value": 6394.9638671875, "min": 6342.95703125, "max": 42662.6640625, "count": 74 }, "Pyramids.Step.mean": { "value": 2219894.0, "min": 29952.0, "max": 2219894.0, "count": 74 }, "Pyramids.Step.sum": { "value": 2219894.0, "min": 29952.0, "max": 2219894.0, "count": 74 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7108884453773499, "min": -0.10718224197626114, "max": 0.7917513251304626, "count": 74 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 204.73587036132812, "min": -25.830921173095703, "max": 232.68447875976562, "count": 74 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.002068731002509594, "min": -0.022476624697446823, "max": 0.718090832233429, "count": 74 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5957944989204407, "min": -6.315931797027588, "max": 170.18753051757812, "count": 74 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06896385410024473, "min": 0.06306390306313656, "max": 0.07312573167369041, "count": 74 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.034457811503671, "min": 0.505250734832384, "max": 1.0886483086893957, "count": 74 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014182371119709892, "min": 0.00018780713212033948, "max": 0.022046837682957454, "count": 74 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2127355667956484, "min": 0.0024414927175644132, "max": 0.2347687060742721, "count": 74 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.948783350407998e-05, "min": 7.948783350407998e-05, "max": 0.00029838354339596195, "count": 74 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0011923175025611997, "min": 0.0011554058148650665, "max": 0.0039690149769950325, "count": 74 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12649592, "min": 0.12649592, "max": 0.19946118095238097, "count": 74 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8974388000000002, "min": 1.3962282666666668, "max": 2.797435233333333, "count": 74 }, "Pyramids.Policy.Beta.mean": { "value": 0.002656942408, "min": 0.002656942408, "max": 0.009946171977142856, "count": 74 }, "Pyramids.Policy.Beta.sum": { "value": 0.03985413612, "min": 0.03861497984, "max": 0.13230819617, "count": 74 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004872409626841545, "min": 0.004872409626841545, "max": 0.5501860976219177, "count": 74 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07308614253997803, "min": 0.06851315498352051, "max": 3.8513028621673584, "count": 74 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 267.92857142857144, "min": 239.40869565217392, "max": 999.0, "count": 74 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30008.0, "min": 15984.0, "max": 32628.0, "count": 74 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6952178411717926, "min": -1.0000000521540642, "max": 1.756663780145604, "count": 74 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 189.86439821124077, "min": -32.000001668930054, "max": 218.70319747924805, "count": 74 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6952178411717926, "min": -1.0000000521540642, "max": 1.756663780145604, "count": 74 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 189.86439821124077, "min": -32.000001668930054, "max": 218.70319747924805, "count": 74 }, "Pyramids.Policy.RndReward.mean": { "value": 0.020227364534548542, "min": 0.0186800462162927, "max": 17.862700942903757, "count": 74 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2654648278694367, "min": 2.166885361089953, "max": 285.8032150864601, "count": 74 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 74 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 74 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679311364", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --force --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679316493" }, "total": 5128.685583266, "count": 1, "self": 0.37654672500138986, "children": { "run_training.setup": { "total": 0.19419290999985606, "count": 1, "self": 0.19419290999985606 }, "TrainerController.start_learning": { "total": 5128.1148436309995, "count": 1, "self": 2.993000362969724, "children": { "TrainerController._reset_env": { "total": 5.96526085000005, "count": 1, "self": 5.96526085000005 }, "TrainerController.advance": { "total": 5119.012813234029, "count": 145098, "self": 3.3753958423458243, "children": { "env_step": { "total": 3750.0977920628043, "count": 145098, "self": 3513.8051432639236, "children": { "SubprocessEnvManager._take_step": { "total": 234.46264572097107, "count": 145098, "self": 10.283723418860973, "children": { "TorchPolicy.evaluate": { "total": 224.1789223021101, "count": 140391, "self": 224.1789223021101 } } }, "workers": { "total": 1.8300030779096232, "count": 145098, "self": 0.0, "children": { "worker_root": { "total": 5118.116264883935, "count": 145098, "is_parallel": true, "self": 1859.8603183498399, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002644625999892014, "count": 1, "is_parallel": true, "self": 0.0007174199995461095, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019272060003459046, "count": 8, "is_parallel": true, "self": 0.0019272060003459046 } } }, "UnityEnvironment.step": { "total": 0.0464308959999471, "count": 1, "is_parallel": true, "self": 0.0005561479993048124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004710110001724388, "count": 1, "is_parallel": true, "self": 0.0004710110001724388 }, "communicator.exchange": { "total": 0.04371357200034254, "count": 1, "is_parallel": true, "self": 0.04371357200034254 }, "steps_from_proto": { "total": 0.0016901650001273083, "count": 1, "is_parallel": true, "self": 0.000376553001387947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013136119987393613, "count": 8, "is_parallel": true, "self": 0.0013136119987393613 } } } } } } }, "UnityEnvironment.step": { "total": 3258.2559465340955, "count": 145097, "is_parallel": true, "self": 68.57586587011201, "children": { "UnityEnvironment._generate_step_input": { "total": 49.47966687392545, "count": 145097, "is_parallel": true, "self": 49.47966687392545 }, "communicator.exchange": { "total": 2939.0468410551134, "count": 145097, "is_parallel": true, "self": 2939.0468410551134 }, "steps_from_proto": { "total": 201.15357273494465, "count": 145097, "is_parallel": true, "self": 42.925451134095965, "children": { "_process_rank_one_or_two_observation": { "total": 158.22812160084868, "count": 1160776, "is_parallel": true, "self": 158.22812160084868 } } } } } } } } } } }, "trainer_advance": { "total": 1365.539625328879, "count": 145098, "self": 5.832565513886038, "children": { "process_trajectory": { "total": 260.18479623999565, "count": 145098, "self": 259.80453503099534, "children": { "RLTrainer._checkpoint": { "total": 0.38026120900030946, "count": 4, "self": 0.38026120900030946 } } }, "_update_policy": { "total": 1099.5222635749974, "count": 1034, "self": 699.7570022299469, "children": { "TorchPPOOptimizer.update": { "total": 399.7652613450505, "count": 51205, "self": 399.7652613450505 } } } } } } }, "trainer_threads": { "total": 3.5860002753906883e-06, "count": 1, "self": 3.5860002753906883e-06 }, "TrainerController._save_models": { "total": 0.14376559800075484, "count": 1, "self": 0.0038810860005469294, "children": { "RLTrainer._checkpoint": { "total": 0.1398845120002079, "count": 1, "self": 0.1398845120002079 } } } } } } }