{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.416933536529541, "min": 0.416933536529541, "max": 1.3051453828811646, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12534.689453125, "min": 12534.689453125, "max": 39592.890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29933.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29933.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5794492959976196, "min": -0.08567088097333908, "max": 0.6038448214530945, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.3485565185547, "min": -20.59337615966797, "max": 171.49192810058594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006457497365772724, "min": -0.008759520016610622, "max": 0.3310072422027588, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.775811791419983, "min": -2.426387071609497, "max": 79.77274322509766, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07184337978841507, "min": 0.0652551326520985, "max": 0.07434623494507933, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.005807317037811, "min": 0.5204236446155553, "max": 1.0917824068866835, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014789379953780293, "min": 0.0009749213001816046, "max": 0.01674599363919004, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2070513193529241, "min": 0.011699055602179256, "max": 0.23444391094866052, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.80247597063572e-06, "min": 7.80247597063572e-06, "max": 0.0002952337301601857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010923466358890009, "min": 0.00010923466358890009, "max": 0.0035070491309836986, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10260079285714288, "min": 0.10260079285714288, "max": 0.19841124285714287, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4364111000000004, "min": 1.3888787, "max": 2.5690162999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026981920642857164, "min": 0.00026981920642857164, "max": 0.009841283161428571, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003777468890000003, "min": 0.003777468890000003, "max": 0.11692472836999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009684900753200054, "min": 0.009684900753200054, "max": 0.45146670937538147, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1355886161327362, "min": 0.1355886161327362, "max": 3.160266876220703, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.79761904761904, "min": 299.8979591836735, "max": 997.258064516129, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29383.0, "min": 16604.0, "max": 34005.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5787499760765404, "min": -0.9336839236559407, "max": 1.6796897803338207, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.6149979904294, "min": -28.94420163333416, "max": 164.60959847271442, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5787499760765404, "min": -0.9336839236559407, "max": 1.6796897803338207, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.6149979904294, "min": -28.94420163333416, "max": 164.60959847271442, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0349734073714076, "min": 0.030282352640657633, "max": 8.586230150040459, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.937766219198238, "min": 2.937766219198238, "max": 145.9659125506878, "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": "1691015435", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691017934" }, "total": 2499.0470324339994, "count": 1, "self": 0.5287334209997425, "children": { "run_training.setup": { "total": 0.06279471599987119, "count": 1, "self": 0.06279471599987119 }, "TrainerController.start_learning": { "total": 2498.4555042969996, "count": 1, "self": 1.75000531605383, "children": { "TrainerController._reset_env": { "total": 5.154349975000059, "count": 1, "self": 5.154349975000059 }, "TrainerController.advance": { "total": 2491.3961120209456, "count": 63954, "self": 1.6450786710570355, "children": { "env_step": { "total": 1796.4559812268872, "count": 63954, "self": 1669.8742564698662, "children": { "SubprocessEnvManager._take_step": { "total": 125.54324896299431, "count": 63954, "self": 5.30949631402882, "children": { "TorchPolicy.evaluate": { "total": 120.23375264896549, "count": 62550, "self": 120.23375264896549 } } }, "workers": { "total": 1.0384757940266809, "count": 63954, "self": 0.0, "children": { "worker_root": { "total": 2491.941592677109, "count": 63954, "is_parallel": true, "self": 953.0954649701721, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024792899998828943, "count": 1, "is_parallel": true, "self": 0.0006303630000275007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018489269998553937, "count": 8, "is_parallel": true, "self": 0.0018489269998553937 } } }, "UnityEnvironment.step": { "total": 0.04699892999997246, "count": 1, "is_parallel": true, "self": 0.0005417589998160111, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005260830000679562, "count": 1, "is_parallel": true, "self": 0.0005260830000679562 }, "communicator.exchange": { "total": 0.04409403300019221, "count": 1, "is_parallel": true, "self": 0.04409403300019221 }, "steps_from_proto": { "total": 0.0018370549998962815, "count": 1, "is_parallel": true, "self": 0.00036012399982610077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014769310000701807, "count": 8, "is_parallel": true, "self": 0.0014769310000701807 } } } } } } }, "UnityEnvironment.step": { "total": 1538.8461277069368, "count": 63953, "is_parallel": true, "self": 36.662380555963864, "children": { "UnityEnvironment._generate_step_input": { "total": 24.51125172294269, "count": 63953, "is_parallel": true, "self": 24.51125172294269 }, "communicator.exchange": { "total": 1364.5040628959523, "count": 63953, "is_parallel": true, "self": 1364.5040628959523 }, "steps_from_proto": { "total": 113.16843253207799, "count": 63953, "is_parallel": true, "self": 22.948820030010438, "children": { "_process_rank_one_or_two_observation": { "total": 90.21961250206755, "count": 511624, "is_parallel": true, "self": 90.21961250206755 } } } } } } } } } } }, "trainer_advance": { "total": 693.2950521230014, "count": 63954, "self": 3.1965787379849644, "children": { "process_trajectory": { "total": 118.15620308201892, "count": 63954, "self": 117.88694117101863, "children": { "RLTrainer._checkpoint": { "total": 0.2692619110002852, "count": 2, "self": 0.2692619110002852 } } }, "_update_policy": { "total": 571.9422703029975, "count": 452, "self": 373.33335896498966, "children": { "TorchPPOOptimizer.update": { "total": 198.60891133800783, "count": 22833, "self": 198.60891133800783 } } } } } } }, "trainer_threads": { "total": 1.422000423190184e-06, "count": 1, "self": 1.422000423190184e-06 }, "TrainerController._save_models": { "total": 0.15503556299972843, "count": 1, "self": 0.001925376999679429, "children": { "RLTrainer._checkpoint": { "total": 0.153110186000049, "count": 1, "self": 0.153110186000049 } } } } } } }