{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44668060541152954, "min": 0.4227876663208008, "max": 1.5060404539108276, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13421.8583984375, "min": 12575.396484375, "max": 45687.2421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1975048929452896, "min": -0.11057180166244507, "max": 0.22375167906284332, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 49.77123260498047, "min": -26.647804260253906, "max": 56.16167068481445, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009416444227099419, "min": -0.009416444227099419, "max": 0.479718416929245, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.372943878173828, "min": -2.372943878173828, "max": 113.69326782226562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07097203882488733, "min": 0.06435141088031766, "max": 0.07345575892212787, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0645805823733099, "min": 0.46211560249202166, "max": 1.0651938794277764, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00915339125381757, "min": 7.161654351395185e-05, "max": 0.01793512577913131, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13730086880726355, "min": 0.0009310150656813741, "max": 0.13730086880726355, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4531175156599945e-06, "min": 7.4531175156599945e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011179676273489992, "min": 0.00011179676273489992, "max": 0.0032523281158906995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248434000000001, "min": 0.10248434000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372651000000002, "min": 1.3886848, "max": 2.3841093000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002581855659999998, "min": 0.0002581855659999998, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003872783489999997, "min": 0.003872783489999997, "max": 0.10843251907000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017269345000386238, "min": 0.01711292378604412, "max": 0.666689395904541, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2590401768684387, "min": 0.2395809292793274, "max": 4.666825771331787, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 643.3333333333334, "min": 643.3333333333334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30880.0, "min": 15984.0, "max": 33837.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6239318822292571, "min": -1.0000000521540642, "max": 0.6337043158710003, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 29.324798464775085, "min": -31.998801678419113, "max": 29.324798464775085, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6239318822292571, "min": -1.0000000521540642, "max": 0.6337043158710003, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 29.324798464775085, "min": -31.998801678419113, "max": 29.324798464775085, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11695967856150596, "min": 0.11695967856150596, "max": 15.128080470487475, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.49710489239078, "min": 5.37399458726577, "max": 242.0492875277996, "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": "1750357714", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750359829" }, "total": 2115.281408865, "count": 1, "self": 0.5293411339998784, "children": { "run_training.setup": { "total": 0.03022779699995226, "count": 1, "self": 0.03022779699995226 }, "TrainerController.start_learning": { "total": 2114.721839934, "count": 1, "self": 1.289498428026036, "children": { "TrainerController._reset_env": { "total": 2.2462209899999834, "count": 1, "self": 2.2462209899999834 }, "TrainerController.advance": { "total": 2111.101807522974, "count": 63210, "self": 1.3419533608966958, "children": { "env_step": { "total": 1472.4646293570465, "count": 63210, "self": 1324.6814583340945, "children": { "SubprocessEnvManager._take_step": { "total": 147.00674505796133, "count": 63210, "self": 4.485285592901164, "children": { "TorchPolicy.evaluate": { "total": 142.52145946506016, "count": 62564, "self": 142.52145946506016 } } }, "workers": { "total": 0.7764259649907217, "count": 63210, "self": 0.0, "children": { "worker_root": { "total": 2109.925625046035, "count": 63210, "is_parallel": true, "self": 892.9918340640615, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019700829998328118, "count": 1, "is_parallel": true, "self": 0.0006936769993899361, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012764060004428757, "count": 8, "is_parallel": true, "self": 0.0012764060004428757 } } }, "UnityEnvironment.step": { "total": 0.05576026600010664, "count": 1, "is_parallel": true, "self": 0.0005671290002737805, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005048789998909342, "count": 1, "is_parallel": true, "self": 0.0005048789998909342 }, "communicator.exchange": { "total": 0.052805441999908, "count": 1, "is_parallel": true, "self": 0.052805441999908 }, "steps_from_proto": { "total": 0.0018828160000339267, "count": 1, "is_parallel": true, "self": 0.00041060099965761765, "children": { "_process_rank_one_or_two_observation": { "total": 0.001472215000376309, "count": 8, "is_parallel": true, "self": 0.001472215000376309 } } } } } } }, "UnityEnvironment.step": { "total": 1216.9337909819733, "count": 63209, "is_parallel": true, "self": 31.229983804933454, "children": { "UnityEnvironment._generate_step_input": { "total": 22.902633015054562, "count": 63209, "is_parallel": true, "self": 22.902633015054562 }, "communicator.exchange": { "total": 1068.3773713039736, "count": 63209, "is_parallel": true, "self": 1068.3773713039736 }, "steps_from_proto": { "total": 94.42380285801164, "count": 63209, "is_parallel": true, "self": 18.832699475198524, "children": { "_process_rank_one_or_two_observation": { "total": 75.59110338281312, "count": 505672, "is_parallel": true, "self": 75.59110338281312 } } } } } } } } } } }, "trainer_advance": { "total": 637.295224805031, "count": 63210, "self": 2.3282246579790353, "children": { "process_trajectory": { "total": 120.90445819705246, "count": 63210, "self": 120.70451934005223, "children": { "RLTrainer._checkpoint": { "total": 0.19993885700023384, "count": 2, "self": 0.19993885700023384 } } }, "_update_policy": { "total": 514.0625419499995, "count": 440, "self": 287.27704926898764, "children": { "TorchPPOOptimizer.update": { "total": 226.78549268101187, "count": 22800, "self": 226.78549268101187 } } } } } } }, "trainer_threads": { "total": 9.039999895321671e-07, "count": 1, "self": 9.039999895321671e-07 }, "TrainerController._save_models": { "total": 0.08431208899992271, "count": 1, "self": 0.001078752000012173, "children": { "RLTrainer._checkpoint": { "total": 0.08323333699991053, "count": 1, "self": 0.08323333699991053 } } } } } } }