{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4536501467227936, "min": 0.4481290876865387, "max": 1.4486898183822632, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13558.6953125, "min": 13451.04296875, "max": 43947.453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38248369097709656, "min": -0.10173966735601425, "max": 0.42480307817459106, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 100.21072387695312, "min": -24.51926040649414, "max": 111.72321319580078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018510952591896057, "min": 0.015417182818055153, "max": 0.5189533829689026, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.849869728088379, "min": 4.054718971252441, "max": 122.99195861816406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06963493651543327, "min": 0.06484056078627183, "max": 0.07312436407246789, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9748891112160659, "min": 0.4890327725722388, "max": 1.0454616449646623, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014133235305939514, "min": 0.0005144786328995766, "max": 0.014133235305939514, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1978652942831532, "min": 0.006688222227694496, "max": 0.1978652942831532, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.634818883664284e-06, "min": 7.634818883664284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010688746437129998, "min": 0.00010688746437129998, "max": 0.0036328138890620986, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254490714285715, "min": 0.10254490714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356287, "min": 1.3886848, "max": 2.6109378999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026423622357142856, "min": 0.00026423622357142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036993071299999997, "min": 0.0036993071299999997, "max": 0.12111269620999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012681729160249233, "min": 0.012681729160249233, "max": 0.5785948038101196, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17754420638084412, "min": 0.17754420638084412, "max": 4.050163745880127, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 471.4, "min": 417.05797101449275, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30641.0, "min": 15984.0, "max": 32707.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3216787595866304, "min": -1.0000000521540642, "max": 1.4326305334559746, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.23079813271761, "min": -29.672001615166664, "max": 103.14939840883017, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3216787595866304, "min": -1.0000000521540642, "max": 1.4326305334559746, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.23079813271761, "min": -29.672001615166664, "max": 103.14939840883017, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06073080798870995, "min": 0.05868019672861385, "max": 11.648794915527105, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.008233327254857, "min": 3.9902533775457414, "max": 186.38071864843369, "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": "1745764369", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745766668" }, "total": 2299.1279242120004, "count": 1, "self": 0.47584278000022096, "children": { "run_training.setup": { "total": 0.020207751000270946, "count": 1, "self": 0.020207751000270946 }, "TrainerController.start_learning": { "total": 2298.631873681, "count": 1, "self": 1.728249254962975, "children": { "TrainerController._reset_env": { "total": 2.309385551000105, "count": 1, "self": 2.309385551000105 }, "TrainerController.advance": { "total": 2294.504890766036, "count": 63527, "self": 1.749962717042763, "children": { "env_step": { "total": 1601.1431607259606, "count": 63527, "self": 1424.2618248699428, "children": { "SubprocessEnvManager._take_step": { "total": 175.8735926189479, "count": 63527, "self": 5.2581211779483965, "children": { "TorchPolicy.evaluate": { "total": 170.6154714409995, "count": 62568, "self": 170.6154714409995 } } }, "workers": { "total": 1.007743237069917, "count": 63527, "self": 0.0, "children": { "worker_root": { "total": 2292.7128097279833, "count": 63527, "is_parallel": true, "self": 996.4291927079212, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020728999998027575, "count": 1, "is_parallel": true, "self": 0.0006981940000514442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013747059997513134, "count": 8, "is_parallel": true, "self": 0.0013747059997513134 } } }, "UnityEnvironment.step": { "total": 0.05503041199972358, "count": 1, "is_parallel": true, "self": 0.000566637999327213, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047038599996085395, "count": 1, "is_parallel": true, "self": 0.00047038599996085395 }, "communicator.exchange": { "total": 0.05212779800012868, "count": 1, "is_parallel": true, "self": 0.05212779800012868 }, "steps_from_proto": { "total": 0.0018655900003068382, "count": 1, "is_parallel": true, "self": 0.00045312200018088333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014124680001259549, "count": 8, "is_parallel": true, "self": 0.0014124680001259549 } } } } } } }, "UnityEnvironment.step": { "total": 1296.2836170200621, "count": 63526, "is_parallel": true, "self": 33.53246748706624, "children": { "UnityEnvironment._generate_step_input": { "total": 24.48016998103958, "count": 63526, "is_parallel": true, "self": 24.48016998103958 }, "communicator.exchange": { "total": 1133.9422807490305, "count": 63526, "is_parallel": true, "self": 1133.9422807490305 }, "steps_from_proto": { "total": 104.32869880292583, "count": 63526, "is_parallel": true, "self": 22.368240735874224, "children": { "_process_rank_one_or_two_observation": { "total": 81.9604580670516, "count": 508208, "is_parallel": true, "self": 81.9604580670516 } } } } } } } } } } }, "trainer_advance": { "total": 691.6117673230328, "count": 63527, "self": 3.1357682780039795, "children": { "process_trajectory": { "total": 134.79168214203128, "count": 63527, "self": 134.5410315480308, "children": { "RLTrainer._checkpoint": { "total": 0.25065059400048995, "count": 2, "self": 0.25065059400048995 } } }, "_update_policy": { "total": 553.6843169029976, "count": 451, "self": 305.41758714700154, "children": { "TorchPPOOptimizer.update": { "total": 248.26672975599604, "count": 22785, "self": 248.26672975599604 } } } } } } }, "trainer_threads": { "total": 9.22000253922306e-07, "count": 1, "self": 9.22000253922306e-07 }, "TrainerController._save_models": { "total": 0.08934718700038502, "count": 1, "self": 0.00141494200033776, "children": { "RLTrainer._checkpoint": { "total": 0.08793224500004726, "count": 1, "self": 0.08793224500004726 } } } } } } }