{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45640096068382263, "min": 0.45640096068382263, "max": 1.3697680234909058, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13662.8193359375, "min": 13662.8193359375, "max": 41553.28125, "count": 33 }, "Pyramids.Step.mean": { "value": 989976.0, "min": 29886.0, "max": 989976.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989976.0, "min": 29886.0, "max": 989976.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5490691065788269, "min": -0.08154668658971786, "max": 0.5490691065788269, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 152.09214782714844, "min": -19.652751922607422, "max": 153.30557250976562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02444746531546116, "min": -0.08219421654939651, "max": 0.40119850635528564, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.771947860717773, "min": -21.37049674987793, "max": 95.08404541015625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07201626677295495, "min": 0.0651014682953246, "max": 0.07343410766631017, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0082277348213693, "min": 0.4929464717563536, "max": 1.1015116149946527, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015708267707460827, "min": 0.0009772615482941118, "max": 0.017183235051713826, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21991574790445156, "min": 0.012704400127823453, "max": 0.21991574790445156, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.674376013335709e-06, "min": 7.674376013335709e-06, "max": 0.0002952357444452286, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010744126418669993, "min": 0.00010744126418669993, "max": 0.0034926925357691993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255809285714286, "min": 0.10255809285714286, "max": 0.19841191428571428, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358133, "min": 1.3888833999999999, "max": 2.4827223000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002655534764285713, "min": 0.0002655534764285713, "max": 0.009841350237142856, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037177486699999985, "min": 0.0037177486699999985, "max": 0.11643665692000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015375062823295593, "min": 0.015156462788581848, "max": 0.6093188524246216, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2152508795261383, "min": 0.21407462656497955, "max": 4.265232086181641, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.9222222222222, "min": 334.06666666666666, "max": 994.375, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30503.0, "min": 16685.0, "max": 33119.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5721710885564486, "min": -0.9327313036192209, "max": 1.643699984997511, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 141.49539797008038, "min": -29.847401715815067, "max": 147.93299864977598, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5721710885564486, "min": -0.9327313036192209, "max": 1.643699984997511, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 141.49539797008038, "min": -29.847401715815067, "max": 147.93299864977598, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.053242837997580256, "min": 0.05301728558139682, "max": 13.531756099532632, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.791855419782223, "min": 4.578578385378933, "max": 230.03985369205475, "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": "1753913891", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753916104" }, "total": 2212.6931678770006, "count": 1, "self": 0.4818141790010486, "children": { "run_training.setup": { "total": 0.020071090999863372, "count": 1, "self": 0.020071090999863372 }, "TrainerController.start_learning": { "total": 2212.1912826069997, "count": 1, "self": 1.5228215809866015, "children": { "TrainerController._reset_env": { "total": 2.144158698999945, "count": 1, "self": 2.144158698999945 }, "TrainerController.advance": { "total": 2208.4371275810136, "count": 63837, "self": 1.5904912501259787, "children": { "env_step": { "total": 1550.25394859798, "count": 63837, "self": 1394.9204709930218, "children": { "SubprocessEnvManager._take_step": { "total": 154.46464557194713, "count": 63837, "self": 4.76608148102423, "children": { "TorchPolicy.evaluate": { "total": 149.6985640909229, "count": 62553, "self": 149.6985640909229 } } }, "workers": { "total": 0.868832033011131, "count": 63837, "self": 0.0, "children": { "worker_root": { "total": 2206.4434149181097, "count": 63837, "is_parallel": true, "self": 929.4399365099471, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002037053000094602, "count": 1, "is_parallel": true, "self": 0.0006222520000846998, "children": { "_process_rank_one_or_two_observation": { "total": 0.001414801000009902, "count": 8, "is_parallel": true, "self": 0.001414801000009902 } } }, "UnityEnvironment.step": { "total": 0.04675177099989014, "count": 1, "is_parallel": true, "self": 0.0006084999999984575, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004550200001176563, "count": 1, "is_parallel": true, "self": 0.0004550200001176563 }, "communicator.exchange": { "total": 0.04406719600001452, "count": 1, "is_parallel": true, "self": 0.04406719600001452 }, "steps_from_proto": { "total": 0.001621054999759508, "count": 1, "is_parallel": true, "self": 0.00036444699981075246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012566079999487556, "count": 8, "is_parallel": true, "self": 0.0012566079999487556 } } } } } } }, "UnityEnvironment.step": { "total": 1277.0034784081627, "count": 63836, "is_parallel": true, "self": 32.048478716222235, "children": { "UnityEnvironment._generate_step_input": { "total": 23.3247484108947, "count": 63836, "is_parallel": true, "self": 23.3247484108947 }, "communicator.exchange": { "total": 1123.7795080210335, "count": 63836, "is_parallel": true, "self": 1123.7795080210335 }, "steps_from_proto": { "total": 97.85074326001222, "count": 63836, "is_parallel": true, "self": 20.270147341882875, "children": { "_process_rank_one_or_two_observation": { "total": 77.58059591812935, "count": 510688, "is_parallel": true, "self": 77.58059591812935 } } } } } } } } } } }, "trainer_advance": { "total": 656.5926877329075, "count": 63837, "self": 2.819976132929696, "children": { "process_trajectory": { "total": 128.38392167197662, "count": 63837, "self": 128.18287220597676, "children": { "RLTrainer._checkpoint": { "total": 0.2010494659998585, "count": 2, "self": 0.2010494659998585 } } }, "_update_policy": { "total": 525.3887899280012, "count": 454, "self": 293.27120731400646, "children": { "TorchPPOOptimizer.update": { "total": 232.11758261399473, "count": 22773, "self": 232.11758261399473 } } } } } } }, "trainer_threads": { "total": 1.0969997674692422e-06, "count": 1, "self": 1.0969997674692422e-06 }, "TrainerController._save_models": { "total": 0.08717364899985114, "count": 1, "self": 0.0011968329999945126, "children": { "RLTrainer._checkpoint": { "total": 0.08597681599985663, "count": 1, "self": 0.08597681599985663 } } } } } } }