{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4764539897441864, "min": 0.4764539897441864, "max": 1.4272775650024414, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14385.0986328125, "min": 14385.0986328125, "max": 43297.890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989940.0, "min": 29980.0, "max": 989940.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989940.0, "min": 29980.0, "max": 989940.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5667742490768433, "min": -0.08340947329998016, "max": 0.6606265306472778, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.13002014160156, "min": -20.101682662963867, "max": 190.26043701171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.11515995115041733, "min": -0.003017711453139782, "max": 0.5006617903709412, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 32.1296272277832, "min": -0.8027112483978271, "max": 119.15750122070312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06712305085689182, "min": 0.06488227691640269, "max": 0.07764958733757185, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9397227119964856, "min": 0.5435471113630029, "max": 1.1090968950844473, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017082306797549664, "min": 0.0006127794450074022, "max": 0.017082306797549664, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23915229516569528, "min": 0.007966132785096228, "max": 0.24142436902426806, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.70523314590714e-06, "min": 7.70523314590714e-06, "max": 0.0002952372015876, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010787326404269997, "min": 0.00010787326404269997, "max": 0.0036340465886512, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256837857142857, "min": 0.10256837857142857, "max": 0.1984124, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359573, "min": 1.3888867999999999, "max": 2.6113488000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002665810192857142, "min": 0.0002665810192857142, "max": 0.009841398759999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037321342699999987, "min": 0.0037321342699999987, "max": 0.12115374512, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011156298220157623, "min": 0.011127087287604809, "max": 0.4877972900867462, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15618817508220673, "min": 0.15577922761440277, "max": 3.414581060409546, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 331.80808080808083, "min": 292.0377358490566, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32849.0, "min": 16651.0, "max": 34085.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5841938578808794, "min": -0.9997600515683492, "max": 1.6676139868795872, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 155.25099807232618, "min": -29.992801547050476, "max": 175.10119865834713, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5841938578808794, "min": -0.9997600515683492, "max": 1.6676139868795872, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 155.25099807232618, "min": -29.992801547050476, "max": 175.10119865834713, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03865347308200565, "min": 0.03555533070292133, "max": 10.289797559380531, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.788040362036554, "min": 3.285915789019782, "max": 174.92655850946903, "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": "1725980980", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725984278" }, "total": 3298.5214353949996, "count": 1, "self": 0.6432477890002701, "children": { "run_training.setup": { "total": 0.07870711799932906, "count": 1, "self": 0.07870711799932906 }, "TrainerController.start_learning": { "total": 3297.799480488, "count": 1, "self": 2.38693228689408, "children": { "TrainerController._reset_env": { "total": 2.4741040600001725, "count": 1, "self": 2.4741040600001725 }, "TrainerController.advance": { "total": 3292.8451459541047, "count": 63955, "self": 2.5633692985311427, "children": { "env_step": { "total": 2200.050960764842, "count": 63955, "self": 2034.676146306826, "children": { "SubprocessEnvManager._take_step": { "total": 163.89855446397632, "count": 63955, "self": 7.387101810763852, "children": { "TorchPolicy.evaluate": { "total": 156.51145265321247, "count": 62554, "self": 156.51145265321247 } } }, "workers": { "total": 1.4762599940395376, "count": 63955, "self": 0.0, "children": { "worker_root": { "total": 3290.479997236016, "count": 63955, "is_parallel": true, "self": 1448.0561869931362, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003337672000270686, "count": 1, "is_parallel": true, "self": 0.0011844049986393657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021532670016313205, "count": 8, "is_parallel": true, "self": 0.0021532670016313205 } } }, "UnityEnvironment.step": { "total": 0.07182861900037096, "count": 1, "is_parallel": true, "self": 0.001029514000947529, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000576311000259011, "count": 1, "is_parallel": true, "self": 0.000576311000259011 }, "communicator.exchange": { "total": 0.06753455899979599, "count": 1, "is_parallel": true, "self": 0.06753455899979599 }, "steps_from_proto": { "total": 0.002688234999368433, "count": 1, "is_parallel": true, "self": 0.0005794039971078746, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021088310022605583, "count": 8, "is_parallel": true, "self": 0.0021088310022605583 } } } } } } }, "UnityEnvironment.step": { "total": 1842.4238102428799, "count": 63954, "is_parallel": true, "self": 51.89029461487644, "children": { "UnityEnvironment._generate_step_input": { "total": 31.299956191935053, "count": 63954, "is_parallel": true, "self": 31.299956191935053 }, "communicator.exchange": { "total": 1626.961018433999, "count": 63954, "is_parallel": true, "self": 1626.961018433999 }, "steps_from_proto": { "total": 132.27254100206937, "count": 63954, "is_parallel": true, "self": 28.554598322202764, "children": { "_process_rank_one_or_two_observation": { "total": 103.71794267986661, "count": 511632, "is_parallel": true, "self": 103.71794267986661 } } } } } } } } } } }, "trainer_advance": { "total": 1090.2308158907317, "count": 63955, "self": 4.742546684825356, "children": { "process_trajectory": { "total": 171.39340981390433, "count": 63955, "self": 171.14427214490297, "children": { "RLTrainer._checkpoint": { "total": 0.2491376690013567, "count": 2, "self": 0.2491376690013567 } } }, "_update_policy": { "total": 914.094859392002, "count": 457, "self": 374.71823136003695, "children": { "TorchPPOOptimizer.update": { "total": 539.3766280319651, "count": 22767, "self": 539.3766280319651 } } } } } } }, "trainer_threads": { "total": 9.520008461549878e-07, "count": 1, "self": 9.520008461549878e-07 }, "TrainerController._save_models": { "total": 0.09329723500013642, "count": 1, "self": 0.001990328999454505, "children": { "RLTrainer._checkpoint": { "total": 0.09130690600068192, "count": 1, "self": 0.09130690600068192 } } } } } } }