{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14899392426013947, "min": 0.14154666662216187, "max": 1.469590425491333, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4450.74658203125, "min": 4205.634765625, "max": 44581.49609375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999938.0, "min": 29952.0, "max": 2999938.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999938.0, "min": 29952.0, "max": 2999938.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8440512418746948, "min": -0.09592615067958832, "max": 0.885044515132904, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 255.74752807617188, "min": -23.118202209472656, "max": 273.478759765625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010689686983823776, "min": -0.01494053564965725, "max": 0.453840047121048, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2389750480651855, "min": -3.8397176265716553, "max": 107.56008911132812, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06700562342458855, "min": 0.06348029808141292, "max": 0.07382671139848171, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0050843513688281, "min": 0.5054575747023498, "max": 1.0797618163730174, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015212228418148298, "min": 8.37979475309153e-05, "max": 0.018061106186123704, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2281834262722245, "min": 0.0010893733179018988, "max": 0.25285548660573187, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4938395020866675e-06, "min": 1.4938395020866675e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2407592531300014e-05, "min": 2.2407592531300014e-05, "max": 0.003969314076895333, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049791333333333, "min": 0.10049791333333333, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074687, "min": 1.3897045333333333, "max": 2.7976468333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9741542000000046e-05, "min": 5.9741542000000046e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008961231300000006, "min": 0.0008961231300000006, "max": 0.13231815619999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007182967383414507, "min": 0.0067884596064686775, "max": 0.4610530734062195, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10774450749158859, "min": 0.09503843635320663, "max": 3.2273714542388916, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 210.65714285714284, "min": 202.64429530201343, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29492.0, "min": 15984.0, "max": 33094.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7741827211148447, "min": -1.0000000521540642, "max": 1.7972364717641391, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 246.61139823496342, "min": -32.000001668930054, "max": 265.9909978210926, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7741827211148447, "min": -1.0000000521540642, "max": 1.7972364717641391, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 246.61139823496342, "min": -32.000001668930054, "max": 265.9909978210926, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015791983410767145, "min": 0.015114700339759559, "max": 9.06342305522412, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1950856940966332, "min": 2.052132949429506, "max": 145.01476888358593, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742036317", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742043995" }, "total": 7678.033337905001, "count": 1, "self": 0.8168004930003008, "children": { "run_training.setup": { "total": 0.03261949000000186, "count": 1, "self": 0.03261949000000186 }, "TrainerController.start_learning": { "total": 7677.183917922001, "count": 1, "self": 4.337185902196325, "children": { "TrainerController._reset_env": { "total": 3.4295955300000287, "count": 1, "self": 3.4295955300000287 }, "TrainerController.advance": { "total": 7669.289229998803, "count": 195631, "self": 4.532996716976413, "children": { "env_step": { "total": 5557.996925771913, "count": 195631, "self": 5083.469000860885, "children": { "SubprocessEnvManager._take_step": { "total": 472.08499722895795, "count": 195631, "self": 14.133354436008176, "children": { "TorchPolicy.evaluate": { "total": 457.95164279294977, "count": 187551, "self": 457.95164279294977 } } }, "workers": { "total": 2.4429276820699215, "count": 195631, "self": 0.0, "children": { "worker_root": { "total": 7660.68817012587, "count": 195631, "is_parallel": true, "self": 2933.0161362358494, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00487371299999495, "count": 1, "is_parallel": true, "self": 0.0034033119999890005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014704010000059498, "count": 8, "is_parallel": true, "self": 0.0014704010000059498 } } }, "UnityEnvironment.step": { "total": 0.053363071000035234, "count": 1, "is_parallel": true, "self": 0.0006198439999707261, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005489890000376363, "count": 1, "is_parallel": true, "self": 0.0005489890000376363 }, "communicator.exchange": { "total": 0.05020465000001195, "count": 1, "is_parallel": true, "self": 0.05020465000001195 }, "steps_from_proto": { "total": 0.001989588000014919, "count": 1, "is_parallel": true, "self": 0.0005402880000247023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014492999999902167, "count": 8, "is_parallel": true, "self": 0.0014492999999902167 } } } } } } }, "UnityEnvironment.step": { "total": 4727.67203389002, "count": 195630, "is_parallel": true, "self": 100.67153405989575, "children": { "UnityEnvironment._generate_step_input": { "total": 72.05147890296507, "count": 195630, "is_parallel": true, "self": 72.05147890296507 }, "communicator.exchange": { "total": 4252.164997320171, "count": 195630, "is_parallel": true, "self": 4252.164997320171 }, "steps_from_proto": { "total": 302.78402360698846, "count": 195630, "is_parallel": true, "self": 61.50961894100976, "children": { "_process_rank_one_or_two_observation": { "total": 241.2744046659787, "count": 1565040, "is_parallel": true, "self": 241.2744046659787 } } } } } } } } } } }, "trainer_advance": { "total": 2106.7593075099135, "count": 195631, "self": 8.273647630862342, "children": { "process_trajectory": { "total": 413.2497834120718, "count": 195631, "self": 412.4626610690716, "children": { "RLTrainer._checkpoint": { "total": 0.7871223430001919, "count": 6, "self": 0.7871223430001919 } } }, "_update_policy": { "total": 1685.2358764669796, "count": 1390, "self": 921.5129978090536, "children": { "TorchPPOOptimizer.update": { "total": 763.722878657926, "count": 68457, "self": 763.722878657926 } } } } } } }, "trainer_threads": { "total": 1.7500005924375728e-06, "count": 1, "self": 1.7500005924375728e-06 }, "TrainerController._save_models": { "total": 0.1279047409998384, "count": 1, "self": 0.0020838189993810374, "children": { "RLTrainer._checkpoint": { "total": 0.12582092200045736, "count": 1, "self": 0.12582092200045736 } } } } } } }