{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5673972964286804, "min": 0.5464015007019043, "max": 1.4441465139389038, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17139.9375, "min": 16252.166015625, "max": 43809.62890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29914.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29914.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2539699971675873, "min": -0.13872107863426208, "max": 0.2728244364261627, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 64.00044250488281, "min": -33.01561737060547, "max": 70.66152954101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.7916343212127686, "min": -0.053066205233335495, "max": 0.7916343212127686, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 199.49185180664062, "min": -13.478816032409668, "max": 199.49185180664062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06954772667318558, "min": 0.06393200132879891, "max": 0.07212807023565151, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9736681734245982, "min": 0.5476240558373984, "max": 1.042915644541876, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0882994739085381, "min": 0.00019157080355647316, "max": 0.0882994739085381, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.2361926347195333, "min": 0.0026819912497906243, "max": 1.2361926347195333, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.75734741425e-06, "min": 7.75734741425e-06, "max": 0.00029484817671727504, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010860286379950002, "min": 0.00010860286379950002, "max": 0.0035070296309901994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258575000000002, "min": 0.10258575000000002, "max": 0.198282725, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362005000000002, "min": 1.4362005000000002, "max": 2.5690098, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002683164250000001, "min": 0.0002683164250000001, "max": 0.0098284442275, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037564299500000013, "min": 0.0037564299500000013, "max": 0.11692407901999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01579723320901394, "min": 0.01579723320901394, "max": 0.4417945146560669, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22116127610206604, "min": 0.22116127610206604, "max": 3.534356117248535, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 602.7884615384615, "min": 567.6181818181818, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31345.0, "min": 18119.0, "max": 32806.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.858599966391921, "min": -0.9998839228383957, "max": 1.016331877004593, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 44.647198252379894, "min": -31.995201662182808, "max": 54.451798379421234, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.858599966391921, "min": -0.9998839228383957, "max": 1.016331877004593, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 44.647198252379894, "min": -31.995201662182808, "max": 54.451798379421234, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09986195956410554, "min": 0.09489360971149706, "max": 7.281182968302777, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.192821897333488, "min": 4.967892783519346, "max": 138.34247639775276, "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": "1754453639", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/envs/myenv/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": "1754455294" }, "total": 1655.597255494, "count": 1, "self": 0.32189056099969093, "children": { "run_training.setup": { "total": 0.017784541000082754, "count": 1, "self": 0.017784541000082754 }, "TrainerController.start_learning": { "total": 1655.2575803920001, "count": 1, "self": 1.3292818390004868, "children": { "TrainerController._reset_env": { "total": 2.3974768569999014, "count": 1, "self": 2.3974768569999014 }, "TrainerController.advance": { "total": 1651.4497419529998, "count": 63353, "self": 1.2904843699582216, "children": { "env_step": { "total": 1021.6985174190581, "count": 63353, "self": 876.6897607470125, "children": { "SubprocessEnvManager._take_step": { "total": 144.21915195401175, "count": 63353, "self": 4.300529948018038, "children": { "TorchPolicy.evaluate": { "total": 139.9186220059937, "count": 62566, "self": 139.9186220059937 } } }, "workers": { "total": 0.7896047180338428, "count": 63353, "self": 0.0, "children": { "worker_root": { "total": 1652.9560740068969, "count": 63353, "is_parallel": true, "self": 866.9382719439252, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018824029998540937, "count": 1, "is_parallel": true, "self": 0.000653618999876926, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012287839999771677, "count": 8, "is_parallel": true, "self": 0.0012287839999771677 } } }, "UnityEnvironment.step": { "total": 0.03616607300000396, "count": 1, "is_parallel": true, "self": 0.0003587119999792776, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000309047999962786, "count": 1, "is_parallel": true, "self": 0.000309047999962786 }, "communicator.exchange": { "total": 0.03448097599994071, "count": 1, "is_parallel": true, "self": 0.03448097599994071 }, "steps_from_proto": { "total": 0.0010173370001211879, "count": 1, "is_parallel": true, "self": 0.00025160300037896377, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007657339997422241, "count": 8, "is_parallel": true, "self": 0.0007657339997422241 } } } } } } }, "UnityEnvironment.step": { "total": 786.0178020629717, "count": 63352, "is_parallel": true, "self": 20.103903939023212, "children": { "UnityEnvironment._generate_step_input": { "total": 13.976369382005714, "count": 63352, "is_parallel": true, "self": 13.976369382005714 }, "communicator.exchange": { "total": 693.6436575689888, "count": 63352, "is_parallel": true, "self": 693.6436575689888 }, "steps_from_proto": { "total": 58.293871172953914, "count": 63352, "is_parallel": true, "self": 12.659440748961515, "children": { "_process_rank_one_or_two_observation": { "total": 45.6344304239924, "count": 506816, "is_parallel": true, "self": 45.6344304239924 } } } } } } } } } } }, "trainer_advance": { "total": 628.4607401639835, "count": 63353, "self": 2.4418183519944705, "children": { "process_trajectory": { "total": 114.94542354899545, "count": 63353, "self": 114.75538992699535, "children": { "RLTrainer._checkpoint": { "total": 0.19003362200010088, "count": 2, "self": 0.19003362200010088 } } }, "_update_policy": { "total": 511.07349826299355, "count": 452, "self": 281.2812915090067, "children": { "TorchPPOOptimizer.update": { "total": 229.79220675398687, "count": 22743, "self": 229.79220675398687 } } } } } } }, "trainer_threads": { "total": 1.0829999155248515e-06, "count": 1, "self": 1.0829999155248515e-06 }, "TrainerController._save_models": { "total": 0.08107866000000286, "count": 1, "self": 0.001282104999972944, "children": { "RLTrainer._checkpoint": { "total": 0.07979655500002991, "count": 1, "self": 0.07979655500002991 } } } } } } }