{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21264386177062988, "min": 0.21264386177062988, "max": 1.3796383142471313, "count": 53 }, "Pyramids.Policy.Entropy.sum": { "value": 6335.0859375, "min": 6335.0859375, "max": 41852.70703125, "count": 53 }, "Pyramids.Step.mean": { "value": 1589877.0, "min": 29880.0, "max": 1589877.0, "count": 53 }, "Pyramids.Step.sum": { "value": 1589877.0, "min": 29880.0, "max": 1589877.0, "count": 53 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.696537971496582, "min": -0.11746654659509659, "max": 0.750348687171936, "count": 53 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 200.60293579101562, "min": -28.191970825195312, "max": 219.85215759277344, "count": 53 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0036463732831180096, "min": -0.03055771254003048, "max": 0.4236472547054291, "count": 53 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.050155520439148, "min": -8.006120681762695, "max": 100.4043960571289, "count": 53 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06995002410188872, "min": 0.0646751906738953, "max": 0.07371931840748466, "count": 53 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9793003374264421, "min": 0.6433943956354526, "max": 1.0735462537025646, "count": 53 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014612637450530501, "min": 0.0004798945839882884, "max": 0.016644984183325766, "count": 53 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20457692430742702, "min": 0.0062386295918477495, "max": 0.2423072722546446, "count": 53 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014244332394748097, "min": 0.00014244332394748097, "max": 0.0002984270894131926, "count": 53 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0019942065352647337, "min": 0.0019942065352647337, "max": 0.003982433772522133, "count": 53 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14748109047619049, "min": 0.14748109047619049, "max": 0.1994756962962963, "count": 53 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0647352666666667, "min": 1.7952812666666667, "max": 2.827477866666667, "count": 53 }, "Pyramids.Policy.Beta.mean": { "value": 0.004753360938571428, "min": 0.004753360938571428, "max": 0.009947622060000001, "count": 53 }, "Pyramids.Policy.Beta.sum": { "value": 0.06654705313999999, "min": 0.06654705313999999, "max": 0.13276503888000002, "count": 53 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011418131180107594, "min": 0.011025588028132915, "max": 0.5400583148002625, "count": 53 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15985383093357086, "min": 0.15435823798179626, "max": 4.860524654388428, "count": 53 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 258.28333333333336, "min": 255.16949152542372, "max": 999.0, "count": 53 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30994.0, "min": 15911.0, "max": 32726.0, "count": 53 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7083733105411132, "min": -0.9999742459866309, "max": 1.7388610937805087, "count": 53 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.0047972649336, "min": -30.999201625585556, "max": 205.0047972649336, "count": 53 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7083733105411132, "min": -0.9999742459866309, "max": 1.7388610937805087, "count": 53 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.0047972649336, "min": -30.999201625585556, "max": 205.0047972649336, "count": 53 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031067348999689177, "min": 0.030972118619671564, "max": 9.107753902673721, "count": 53 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7280818799627014, "min": 3.300648847114644, "max": 154.83181634545326, "count": 53 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 53 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 53 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1788931619", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/root/.cache/uv/builds-v0/.tmp1fqbiO/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1788937814" }, "total": 6195.675619174999, "count": 1, "self": 0.46610096900076314, "children": { "run_training.setup": { "total": 0.027055703999849356, "count": 1, "self": 0.027055703999849356 }, "TrainerController.start_learning": { "total": 6195.182462501999, "count": 1, "self": 3.966522748947682, "children": { "TrainerController._reset_env": { "total": 1.3117507449996992, "count": 1, "self": 1.3117507449996992 }, "TrainerController.advance": { "total": 6189.723418938051, "count": 103160, "self": 3.9304608054480923, "children": { "env_step": { "total": 4378.185133947631, "count": 103160, "self": 4168.366821637129, "children": { "SubprocessEnvManager._take_step": { "total": 207.5124902977691, "count": 103160, "self": 11.098559461757759, "children": { "TorchPolicy.evaluate": { "total": 196.41393083601133, "count": 100053, "self": 196.41393083601133 } } }, "workers": { "total": 2.305822012732733, "count": 103160, "self": 0.0, "children": { "worker_root": { "total": 6179.046863565995, "count": 103160, "is_parallel": true, "self": 2305.6565264611195, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0044336419996398035, "count": 1, "is_parallel": true, "self": 0.001563513000292005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028701289993477985, "count": 8, "is_parallel": true, "self": 0.0028701289993477985 } } }, "UnityEnvironment.step": { "total": 0.0777303159998155, "count": 1, "is_parallel": true, "self": 0.0007172639998316299, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006812759997956164, "count": 1, "is_parallel": true, "self": 0.0006812759997956164 }, "communicator.exchange": { "total": 0.07397822700022516, "count": 1, "is_parallel": true, "self": 0.07397822700022516 }, "steps_from_proto": { "total": 0.0023535489999630954, "count": 1, "is_parallel": true, "self": 0.000462914000308956, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018906349996541394, "count": 8, "is_parallel": true, "self": 0.0018906349996541394 } } } } } } }, "UnityEnvironment.step": { "total": 3873.390337104876, "count": 103159, "is_parallel": true, "self": 73.43098367807852, "children": { "UnityEnvironment._generate_step_input": { "total": 51.244720728937864, "count": 103159, "is_parallel": true, "self": 51.244720728937864 }, "communicator.exchange": { "total": 3491.349083196751, "count": 103159, "is_parallel": true, "self": 3491.349083196751 }, "steps_from_proto": { "total": 257.3655495011085, "count": 103159, "is_parallel": true, "self": 52.41919060507689, "children": { "_process_rank_one_or_two_observation": { "total": 204.9463588960316, "count": 825272, "is_parallel": true, "self": 204.9463588960316 } } } } } } } } } } }, "trainer_advance": { "total": 1807.6078241849714, "count": 103160, "self": 6.9062353961448935, "children": { "process_trajectory": { "total": 231.1448844208221, "count": 103160, "self": 230.70066016182182, "children": { "RLTrainer._checkpoint": { "total": 0.4442242590002934, "count": 3, "self": 0.4442242590002934 } } }, "_update_policy": { "total": 1569.5567043680044, "count": 742, "self": 686.5385135660549, "children": { "TorchPPOOptimizer.update": { "total": 883.0181908019495, "count": 36473, "self": 883.0181908019495 } } } } } } }, "trainer_threads": { "total": 2.0469997252803296e-06, "count": 1, "self": 2.0469997252803296e-06 }, "TrainerController._save_models": { "total": 0.18076802300129202, "count": 1, "self": 0.002423499001452001, "children": { "RLTrainer._checkpoint": { "total": 0.17834452399984002, "count": 1, "self": 0.17834452399984002 } } } } } } }