|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5328787565231323, |
|
"min": 0.517841100692749, |
|
"max": 1.468865990638733, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 16011.94140625, |
|
"min": 15485.51953125, |
|
"max": 44559.51953125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989887.0, |
|
"min": 29952.0, |
|
"max": 989887.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989887.0, |
|
"min": 29952.0, |
|
"max": 989887.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4811851382255554, |
|
"min": -0.12081677466630936, |
|
"max": 0.583763837814331, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 130.88235473632812, |
|
"min": -29.11684226989746, |
|
"max": 162.8701171875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.022094663232564926, |
|
"min": -0.03961009904742241, |
|
"max": 0.30382704734802246, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -6.009748458862305, |
|
"min": -10.853167533874512, |
|
"max": 72.00701141357422, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06712853484813135, |
|
"min": 0.06414517158104684, |
|
"max": 0.07271406025751356, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9397994878738388, |
|
"min": 0.5089984218025949, |
|
"max": 1.0350850958881588, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01693310606354034, |
|
"min": 0.0005130805122297654, |
|
"max": 0.017434505818589265, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23706348488956475, |
|
"min": 0.006670046658986951, |
|
"max": 0.25682629943185026, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.380226111385711e-06, |
|
"min": 7.380226111385711e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010332316555939996, |
|
"min": 0.00010332316555939996, |
|
"max": 0.0035087132304289993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10246004285714287, |
|
"min": 0.10246004285714287, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4344406000000003, |
|
"min": 1.3886848, |
|
"max": 2.5695710000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025575828142857134, |
|
"min": 0.00025575828142857134, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035806159399999985, |
|
"min": 0.0035806159399999985, |
|
"max": 0.1169801429, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01138848066329956, |
|
"min": 0.01138848066329956, |
|
"max": 0.3892519176006317, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.15943872928619385, |
|
"min": 0.15943872928619385, |
|
"max": 2.7247633934020996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 372.0, |
|
"min": 332.64444444444445, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30876.0, |
|
"min": 15984.0, |
|
"max": 32954.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5074819014912628, |
|
"min": -1.0000000521540642, |
|
"max": 1.640486346388405, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 125.12099782377481, |
|
"min": -29.989001713693142, |
|
"max": 146.061198040843, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5074819014912628, |
|
"min": -1.0000000521540642, |
|
"max": 1.640486346388405, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 125.12099782377481, |
|
"min": -29.989001713693142, |
|
"max": 146.061198040843, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04382486527235842, |
|
"min": 0.04015550765689113, |
|
"max": 8.019810074940324, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.6374638176057488, |
|
"min": 3.5336846738064196, |
|
"max": 128.31696119904518, |
|
"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": "1681084630", |
|
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", |
|
"command_line_arguments": "/home/hussam/miniconda3/envs/hf-course/bin/mlagents-learn ./ml-agents/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": "1681086077" |
|
}, |
|
"total": 1446.8511934559938, |
|
"count": 1, |
|
"self": 0.42134948598686606, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.01325508400623221, |
|
"count": 1, |
|
"self": 0.01325508400623221 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1446.4165888860007, |
|
"count": 1, |
|
"self": 1.39957985363435, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.501554992995807, |
|
"count": 1, |
|
"self": 4.501554992995807 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1440.428844327369, |
|
"count": 63841, |
|
"self": 1.4097100749931997, |
|
"children": { |
|
"env_step": { |
|
"total": 957.4134823645727, |
|
"count": 63841, |
|
"self": 855.5372401778586, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 100.9900175696821, |
|
"count": 63841, |
|
"self": 4.056951188744279, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 96.93306638093782, |
|
"count": 62557, |
|
"self": 96.93306638093782 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.886224617031985, |
|
"count": 63841, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1444.265765129443, |
|
"count": 63841, |
|
"is_parallel": true, |
|
"self": 681.5673130170617, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0012745710118906572, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003797999816015363, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.000894771030289121, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.000894771030289121 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.11427762900711969, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002642350009409711, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00022067100508138537, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00022067100508138537 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.11301803200331051, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.11301803200331051 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0007746909977868199, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002218140143668279, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.000552876983419992, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.000552876983419992 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 762.6984521123813, |
|
"count": 63840, |
|
"is_parallel": true, |
|
"self": 22.593958325320273, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 14.543939641982433, |
|
"count": 63840, |
|
"is_parallel": true, |
|
"self": 14.543939641982433 |
|
}, |
|
"communicator.exchange": { |
|
"total": 659.0978743617743, |
|
"count": 63840, |
|
"is_parallel": true, |
|
"self": 659.0978743617743 |
|
}, |
|
"steps_from_proto": { |
|
"total": 66.46267978330434, |
|
"count": 63840, |
|
"is_parallel": true, |
|
"self": 14.45735713824979, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 52.00532264505455, |
|
"count": 510720, |
|
"is_parallel": true, |
|
"self": 52.00532264505455 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 481.6056518878031, |
|
"count": 63841, |
|
"self": 2.4523376661527436, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 87.16897421363683, |
|
"count": 63841, |
|
"self": 86.76172501863039, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.4072491950064432, |
|
"count": 2, |
|
"self": 0.4072491950064432 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 391.98434000801353, |
|
"count": 452, |
|
"self": 242.12617671153566, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 149.85816329647787, |
|
"count": 22773, |
|
"self": 149.85816329647787 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2880045687779784e-06, |
|
"count": 1, |
|
"self": 1.2880045687779784e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08660842399694957, |
|
"count": 1, |
|
"self": 0.0010562109964666888, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08555221300048288, |
|
"count": 1, |
|
"self": 0.08555221300048288 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |