{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17482934892177582, "min": 0.17420333623886108, "max": 1.5982792377471924, "count": 84 }, "Pyramids.Policy.Entropy.sum": { "value": 5239.2861328125, "min": 5189.86572265625, "max": 38346.4296875, "count": 84 }, "Pyramids.Step.mean": { "value": 2999957.0, "min": 509925.0, "max": 2999957.0, "count": 84 }, "Pyramids.Step.sum": { "value": 2999957.0, "min": 509925.0, "max": 2999957.0, "count": 84 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7689042091369629, "min": -0.14964228868484497, "max": 0.8614444136619568, "count": 84 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 234.51577758789062, "min": -35.70473861694336, "max": 264.46343994140625, "count": 84 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0020513564813882113, "min": -0.03093297779560089, "max": 0.41726115345954895, "count": 84 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.6256637573242188, "min": -7.856976509094238, "max": 100.1426773071289, "count": 84 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06637767469898488, "min": 0.06235508583162161, "max": 0.07530194558322742, "count": 84 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9956651204847732, "min": 0.1367307250426772, "max": 1.0809680807481832, "count": 84 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016830076922714297, "min": 0.00013697546329992298, "max": 0.017540914127104252, "count": 84 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2524511538407144, "min": 0.0017806810228989988, "max": 0.25283179609601464, "count": 84 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4847728384422218e-06, "min": 1.4847728384422218e-06, "max": 0.0002493787168737667, "count": 84 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.227159257663333e-05, "min": 2.227159257663333e-05, "max": 0.0030872145709286004, "count": 84 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049489111111111, "min": 0.10049489111111111, "max": 0.18312623333333333, "count": 84 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074233666666665, "min": 0.36625246666666667, "max": 2.4374331000000002, "count": 84 }, "Pyramids.Policy.Beta.mean": { "value": 5.9439622e-05, "min": 5.9439622e-05, "max": 0.008314310710000002, "count": 84 }, "Pyramids.Policy.Beta.sum": { "value": 0.00089159433, "min": 0.00089159433, "max": 0.10294423286, "count": 84 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007446684874594212, "min": 0.007070202846080065, "max": 0.8641199469566345, "count": 84 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11170027405023575, "min": 0.09898284077644348, "max": 1.9113531112670898, "count": 84 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 84 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 84 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 233.87218045112783, "min": 213.12408759124088, "max": 999.0, "count": 83 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31105.0, "min": 18981.0, "max": 32633.0, "count": 83 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7215393754004529, "min": -1.0000000521540642, "max": 1.786195639034976, "count": 83 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 227.24319755285978, "min": -32.000001668930054, "max": 253.36139796674252, "count": 83 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7215393754004529, "min": -1.0000000521540642, "max": 1.786195639034976, "count": 83 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 227.24319755285978, "min": -32.000001668930054, "max": 253.36139796674252, "count": 83 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017973600814112808, "min": 0.016360701486374255, "max": 6.292424391023815, "count": 83 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3725153074628906, "min": 2.1935658946749754, "max": 201.35758051276207, "count": 83 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739874395", "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 --resume", "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": "1739880960" }, "total": 6564.893774228, "count": 1, "self": 0.5416670360000353, "children": { "run_training.setup": { "total": 0.021810664000440738, "count": 1, "self": 0.021810664000440738 }, "TrainerController.start_learning": { "total": 6564.330296528, "count": 1, "self": 4.346934234961736, "children": { "TrainerController._reset_env": { "total": 2.936605330999555, "count": 1, "self": 2.936605330999555 }, "TrainerController.advance": { "total": 6556.9565665290365, "count": 161807, "self": 4.36184257162131, "children": { "env_step": { "total": 4738.850829515155, "count": 161807, "self": 4294.386342242735, "children": { "SubprocessEnvManager._take_step": { "total": 441.9649625342163, "count": 161807, "self": 13.31593896180948, "children": { "TorchPolicy.evaluate": { "total": 428.6490235724068, "count": 156299, "self": 428.6490235724068 } } }, "workers": { "total": 2.499524738203945, "count": 161807, "self": 0.0, "children": { "worker_root": { "total": 6549.014671803079, "count": 161807, "is_parallel": true, "self": 2580.480464456886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002100775999679172, "count": 1, "is_parallel": true, "self": 0.0006744310012436472, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014263449984355248, "count": 8, "is_parallel": true, "self": 0.0014263449984355248 } } }, "UnityEnvironment.step": { "total": 0.05697112200050469, "count": 1, "is_parallel": true, "self": 0.0004941830011375714, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004356379995442694, "count": 1, "is_parallel": true, "self": 0.0004356379995442694 }, "communicator.exchange": { "total": 0.0546180169994841, "count": 1, "is_parallel": true, "self": 0.0546180169994841 }, "steps_from_proto": { "total": 0.0014232840003387537, "count": 1, "is_parallel": true, "self": 0.0002906259996962035, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011326580006425502, "count": 8, "is_parallel": true, "self": 0.0011326580006425502 } } } } } } }, "UnityEnvironment.step": { "total": 3968.5342073461934, "count": 161806, "is_parallel": true, "self": 87.96226158397258, "children": { "UnityEnvironment._generate_step_input": { "total": 61.19592845652551, "count": 161806, "is_parallel": true, "self": 61.19592845652551 }, "communicator.exchange": { "total": 3560.82909994094, "count": 161806, "is_parallel": true, "self": 3560.82909994094 }, "steps_from_proto": { "total": 258.54691736475525, "count": 161806, "is_parallel": true, "self": 54.16847064481772, "children": { "_process_rank_one_or_two_observation": { "total": 204.37844671993753, "count": 1294448, "is_parallel": true, "self": 204.37844671993753 } } } } } } } } } } }, "trainer_advance": { "total": 1813.7438944422602, "count": 161807, "self": 8.371537257095952, "children": { "process_trajectory": { "total": 343.85949047214217, "count": 161807, "self": 343.31208792414327, "children": { "RLTrainer._checkpoint": { "total": 0.5474025479988995, "count": 5, "self": 0.5474025479988995 } } }, "_update_policy": { "total": 1461.512866713022, "count": 1153, "self": 795.8833492420399, "children": { "TorchPPOOptimizer.update": { "total": 665.6295174709821, "count": 57030, "self": 665.6295174709821 } } } } } } }, "trainer_threads": { "total": 8.29000782687217e-07, "count": 1, "self": 8.29000782687217e-07 }, "TrainerController._save_models": { "total": 0.09018960400135256, "count": 1, "self": 0.002010412999879918, "children": { "RLTrainer._checkpoint": { "total": 0.08817919100147265, "count": 1, "self": 0.08817919100147265 } } } } } } }