{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3619743883609772, "min": 0.3619743883609772, "max": 1.477776050567627, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10859.2314453125, "min": 10859.2314453125, "max": 44829.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989940.0, "min": 29998.0, "max": 989940.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989940.0, "min": 29998.0, "max": 989940.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4302888512611389, "min": -0.11164487153291702, "max": 0.5161469578742981, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.59626007080078, "min": -26.906414031982422, "max": 141.39706420898438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025792287662625313, "min": 0.004031728953123093, "max": 0.3135673403739929, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.809164047241211, "min": 1.0522812604904175, "max": 74.94259643554688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06383570506128532, "min": 0.06383570506128532, "max": 0.07218891482091647, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8936998708579944, "min": 0.4940205282433327, "max": 1.0488072988615993, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015616663270518253, "min": 0.0009742205564260566, "max": 0.015616663270518253, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21863328578725555, "min": 0.013639087789964793, "max": 0.22658032681319323, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.743697418799998e-06, "min": 7.743697418799998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010841176386319996, "min": 0.00010841176386319996, "max": 0.0036324559891813997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258120000000001, "min": 0.10258120000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361368, "min": 1.3886848, "max": 2.6108185999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026786187999999994, "min": 0.00026786187999999994, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037500663199999994, "min": 0.0037500663199999994, "max": 0.12110077814, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006924315821379423, "min": 0.006924315821379423, "max": 0.3074083924293518, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09694042056798935, "min": 0.09694042056798935, "max": 2.1518588066101074, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.4225352112676, "min": 357.0357142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28714.0, "min": 17564.0, "max": 33386.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5132086783431578, "min": -0.9999667187531789, "max": 1.5669368228041811, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.41139880567789, "min": -29.999001562595367, "max": 130.00679821521044, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5132086783431578, "min": -0.9999667187531789, "max": 1.5669368228041811, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.41139880567789, "min": -29.999001562595367, "max": 130.00679821521044, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02865811048305013, "min": 0.02845908599591071, "max": 5.77150567745169, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.977409623330459, "min": 1.977409623330459, "max": 103.88710219413042, "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": "1738329691", "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": "1738331803" }, "total": 2112.7733730809996, "count": 1, "self": 0.48148506799952884, "children": { "run_training.setup": { "total": 0.019447943999693962, "count": 1, "self": 0.019447943999693962 }, "TrainerController.start_learning": { "total": 2112.2724400690004, "count": 1, "self": 1.2790281160250743, "children": { "TrainerController._reset_env": { "total": 2.2354801860001317, "count": 1, "self": 2.2354801860001317 }, "TrainerController.advance": { "total": 2108.673802639976, "count": 63787, "self": 1.3928277617451386, "children": { "env_step": { "total": 1434.5045884678602, "count": 63787, "self": 1286.616573206482, "children": { "SubprocessEnvManager._take_step": { "total": 147.15315202840065, "count": 63787, "self": 4.462415035344748, "children": { "TorchPolicy.evaluate": { "total": 142.6907369930559, "count": 62573, "self": 142.6907369930559 } } }, "workers": { "total": 0.7348632329776592, "count": 63787, "self": 0.0, "children": { "worker_root": { "total": 2107.947478546974, "count": 63787, "is_parallel": true, "self": 926.4992629443586, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002031369000178529, "count": 1, "is_parallel": true, "self": 0.0006411870035663014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013901819966122275, "count": 8, "is_parallel": true, "self": 0.0013901819966122275 } } }, "UnityEnvironment.step": { "total": 0.04626570999971591, "count": 1, "is_parallel": true, "self": 0.0005286409996188013, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006167070005176356, "count": 1, "is_parallel": true, "self": 0.0006167070005176356 }, "communicator.exchange": { "total": 0.04351265500008594, "count": 1, "is_parallel": true, "self": 0.04351265500008594 }, "steps_from_proto": { "total": 0.00160770699949353, "count": 1, "is_parallel": true, "self": 0.0003381299993634457, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012695770001300843, "count": 8, "is_parallel": true, "self": 0.0012695770001300843 } } } } } } }, "UnityEnvironment.step": { "total": 1181.4482156026152, "count": 63786, "is_parallel": true, "self": 30.531888292540316, "children": { "UnityEnvironment._generate_step_input": { "total": 22.371413831129757, "count": 63786, "is_parallel": true, "self": 22.371413831129757 }, "communicator.exchange": { "total": 1037.3113809660754, "count": 63786, "is_parallel": true, "self": 1037.3113809660754 }, "steps_from_proto": { "total": 91.23353251286971, "count": 63786, "is_parallel": true, "self": 17.664840062914664, "children": { "_process_rank_one_or_two_observation": { "total": 73.56869244995505, "count": 510288, "is_parallel": true, "self": 73.56869244995505 } } } } } } } } } } }, "trainer_advance": { "total": 672.7763864103708, "count": 63787, "self": 2.537137395233003, "children": { "process_trajectory": { "total": 126.80684178913907, "count": 63787, "self": 126.50794901513837, "children": { "RLTrainer._checkpoint": { "total": 0.2988927740007057, "count": 2, "self": 0.2988927740007057 } } }, "_update_policy": { "total": 543.4324072259988, "count": 455, "self": 299.73097654920275, "children": { "TorchPPOOptimizer.update": { "total": 243.701430676796, "count": 22767, "self": 243.701430676796 } } } } } } }, "trainer_threads": { "total": 8.249990059994161e-07, "count": 1, "self": 8.249990059994161e-07 }, "TrainerController._save_models": { "total": 0.08412830199995369, "count": 1, "self": 0.00142560099993716, "children": { "RLTrainer._checkpoint": { "total": 0.08270270100001653, "count": 1, "self": 0.08270270100001653 } } } } } } }