{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18535521626472473, "min": 0.17403636872768402, "max": 1.4797165393829346, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5590.3134765625, "min": 5249.81591796875, "max": 44888.6796875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999887.0, "min": 29922.0, "max": 2999887.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999887.0, "min": 29922.0, "max": 2999887.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8328748345375061, "min": -0.1038481667637825, "max": 0.9149202704429626, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 247.36383056640625, "min": -25.131256103515625, "max": 287.28497314453125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014337725937366486, "min": -0.06541164219379425, "max": 0.35815566778182983, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.258304595947266, "min": -17.661144256591797, "max": 84.88289642333984, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07103111432565473, "min": 0.06337840792613596, "max": 0.07297746869827175, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.065466714884821, "min": 0.5108422808879023, "max": 1.0730015888533957, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013715189750636533, "min": 0.00026187829616438767, "max": 0.017055366827471437, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.205727846259548, "min": 0.003142539553972652, "max": 0.23877513558460015, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.519166160311104e-06, "min": 1.519166160311104e-06, "max": 0.0002984114005295333, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.278749240466656e-05, "min": 2.278749240466656e-05, "max": 0.0039695695768101665, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050635555555557, "min": 0.10050635555555557, "max": 0.19947046666666668, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075953333333334, "min": 1.3962932666666668, "max": 2.8124718666666673, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0584919999999754e-05, "min": 6.0584919999999754e-05, "max": 0.009947099619999998, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009087737999999964, "min": 0.0009087737999999964, "max": 0.13232666434999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0063836174085736275, "min": 0.006180214695632458, "max": 0.3896730840206146, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09575425833463669, "min": 0.08652300387620926, "max": 2.7277116775512695, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 221.85714285714286, "min": 196.81045751633988, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27954.0, "min": 16721.0, "max": 32323.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7465763624141535, "min": -0.999903277524056, "max": 1.7946824220990814, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 221.8151980265975, "min": -30.997001603245735, "max": 273.873198479414, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7465763624141535, "min": -0.999903277524056, "max": 1.7946824220990814, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 221.8151980265975, "min": -30.997001603245735, "max": 273.873198479414, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01449265299299269, "min": 0.013690494294619613, "max": 7.311247367192717, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8405669301100716, "min": 1.8405669301100716, "max": 124.29120524227619, "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": "1722240639", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722245863" }, "total": 5223.930010196001, "count": 1, "self": 0.3725842540006852, "children": { "run_training.setup": { "total": 0.05449650799994288, "count": 1, "self": 0.05449650799994288 }, "TrainerController.start_learning": { "total": 5223.502929434, "count": 1, "self": 4.22077262915991, "children": { "TrainerController._reset_env": { "total": 2.0454575560000876, "count": 1, "self": 2.0454575560000876 }, "TrainerController.advance": { "total": 5217.149424316841, "count": 195608, "self": 4.059529022582865, "children": { "env_step": { "total": 3460.5996767411093, "count": 195608, "self": 3082.0289851512716, "children": { "SubprocessEnvManager._take_step": { "total": 375.96389581699225, "count": 195608, "self": 13.558149060980782, "children": { "TorchPolicy.evaluate": { "total": 362.40574675601147, "count": 187559, "self": 362.40574675601147 } } }, "workers": { "total": 2.6067957728456577, "count": 195608, "self": 0.0, "children": { "worker_root": { "total": 5216.689421653077, "count": 195608, "is_parallel": true, "self": 2441.499131032131, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020848729999443094, "count": 1, "is_parallel": true, "self": 0.000647403999778362, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014374690001659474, "count": 8, "is_parallel": true, "self": 0.0014374690001659474 } } }, "UnityEnvironment.step": { "total": 0.03822499900002185, "count": 1, "is_parallel": true, "self": 0.00044477200003711914, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033218499993381556, "count": 1, "is_parallel": true, "self": 0.00033218499993381556 }, "communicator.exchange": { "total": 0.03629049100004522, "count": 1, "is_parallel": true, "self": 0.03629049100004522 }, "steps_from_proto": { "total": 0.0011575510000056966, "count": 1, "is_parallel": true, "self": 0.00026954099996601144, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008880100000396851, "count": 8, "is_parallel": true, "self": 0.0008880100000396851 } } } } } } }, "UnityEnvironment.step": { "total": 2775.190290620946, "count": 195607, "is_parallel": true, "self": 68.2026290299359, "children": { "UnityEnvironment._generate_step_input": { "total": 42.8606724801208, "count": 195607, "is_parallel": true, "self": 42.8606724801208 }, "communicator.exchange": { "total": 2470.3606953088242, "count": 195607, "is_parallel": true, "self": 2470.3606953088242 }, "steps_from_proto": { "total": 193.76629380206532, "count": 195607, "is_parallel": true, "self": 42.12759774883557, "children": { "_process_rank_one_or_two_observation": { "total": 151.63869605322975, "count": 1564856, "is_parallel": true, "self": 151.63869605322975 } } } } } } } } } } }, "trainer_advance": { "total": 1752.4902185531487, "count": 195608, "self": 8.561444220089697, "children": { "process_trajectory": { "total": 359.38304962905727, "count": 195608, "self": 358.8474447750573, "children": { "RLTrainer._checkpoint": { "total": 0.5356048539999847, "count": 6, "self": 0.5356048539999847 } } }, "_update_policy": { "total": 1384.5457247040017, "count": 1402, "self": 820.6991755719698, "children": { "TorchPPOOptimizer.update": { "total": 563.8465491320319, "count": 68394, "self": 563.8465491320319 } } } } } } }, "trainer_threads": { "total": 1.1339998309267685e-06, "count": 1, "self": 1.1339998309267685e-06 }, "TrainerController._save_models": { "total": 0.08727379799984192, "count": 1, "self": 0.0015812700003152713, "children": { "RLTrainer._checkpoint": { "total": 0.08569252799952665, "count": 1, "self": 0.08569252799952665 } } } } } } }