|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.40888598561286926, |
|
"min": 0.40888598561286926, |
|
"max": 1.4832767248153687, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 12076.8564453125, |
|
"min": 12076.8564453125, |
|
"max": 44996.68359375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989875.0, |
|
"min": 29952.0, |
|
"max": 989875.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989875.0, |
|
"min": 29952.0, |
|
"max": 989875.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6013543605804443, |
|
"min": -0.06041796877980232, |
|
"max": 0.62327641248703, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 169.58192443847656, |
|
"min": -14.68156623840332, |
|
"max": 174.51739501953125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.019434195011854172, |
|
"min": 0.00868353433907032, |
|
"max": 0.347851037979126, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.480443000793457, |
|
"min": 2.3358707427978516, |
|
"max": 84.1799545288086, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06965599983509276, |
|
"min": 0.06538904178854996, |
|
"max": 0.07287731882076644, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9751839976912985, |
|
"min": 0.4912734628320824, |
|
"max": 1.0389336003766705, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017883034190855962, |
|
"min": 0.0016251535215964744, |
|
"max": 0.017883034190855962, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.25036247867198347, |
|
"min": 0.01787668873756122, |
|
"max": 0.25036247867198347, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.330533270807149e-06, |
|
"min": 7.330533270807149e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010262746579130008, |
|
"min": 0.00010262746579130008, |
|
"max": 0.0036336154887949, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10244347857142856, |
|
"min": 0.10244347857142856, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4342087, |
|
"min": 1.3886848, |
|
"max": 2.6177692000000006, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002541035092857145, |
|
"min": 0.0002541035092857145, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003557449130000003, |
|
"min": 0.003557449130000003, |
|
"max": 0.12113938949000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01316326204687357, |
|
"min": 0.01308561209589243, |
|
"max": 0.599920928478241, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.18428567051887512, |
|
"min": 0.18428567051887512, |
|
"max": 4.199446678161621, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 305.57608695652175, |
|
"min": 290.48979591836735, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28113.0, |
|
"min": 15984.0, |
|
"max": 33168.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6726782427209874, |
|
"min": -1.0000000521540642, |
|
"max": 1.6910040252136462, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 153.88639833033085, |
|
"min": -27.183401711285114, |
|
"max": 167.40939849615097, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6726782427209874, |
|
"min": -1.0000000521540642, |
|
"max": 1.6910040252136462, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 153.88639833033085, |
|
"min": -27.183401711285114, |
|
"max": 167.40939849615097, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04177115554383541, |
|
"min": 0.04093741817647389, |
|
"max": 11.74573023058474, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.8429463100328576, |
|
"min": 3.8429463100328576, |
|
"max": 187.93168368935585, |
|
"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": "1720850684", |
|
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/home/shinnigus/.local/bin/mlagents-learn /home/shinnigus/huggingface-deeprl/notebooks/unit5/ml-agents/config/ppo/PyramidsRND.yaml --env=/home/shinnigus/huggingface-deeprl/notebooks/unit5/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": "1720852144" |
|
}, |
|
"total": 1460.2105501530023, |
|
"count": 1, |
|
"self": 0.268867318998673, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.029221842996776104, |
|
"count": 1, |
|
"self": 0.029221842996776104 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1459.9124609910068, |
|
"count": 1, |
|
"self": 0.9378263837861596, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.001388735996443, |
|
"count": 1, |
|
"self": 2.001388735996443 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1456.9082653702208, |
|
"count": 64228, |
|
"self": 0.9659237306623254, |
|
"children": { |
|
"env_step": { |
|
"total": 947.8234297667368, |
|
"count": 64228, |
|
"self": 726.5215206150315, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 220.68337140261428, |
|
"count": 64228, |
|
"self": 2.9355536661169026, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 217.74781773649738, |
|
"count": 62539, |
|
"self": 217.74781773649738 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6185377490910469, |
|
"count": 64228, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1457.5740660495794, |
|
"count": 64228, |
|
"is_parallel": true, |
|
"self": 791.3476614686806, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0016271640051854774, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000812960002804175, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008142040023813024, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008142040023813024 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.025172206995193847, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00016871000116225332, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00017386898980475962, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00017386898980475962 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.024359643997740932, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.024359643997740932 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0004699840064859018, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0001287290215259418, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00034125498495996, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.00034125498495996 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 666.2264045808988, |
|
"count": 64227, |
|
"is_parallel": true, |
|
"self": 10.684605578469927, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 7.350291012204252, |
|
"count": 64227, |
|
"is_parallel": true, |
|
"self": 7.350291012204252 |
|
}, |
|
"communicator.exchange": { |
|
"total": 620.4874629875703, |
|
"count": 64227, |
|
"is_parallel": true, |
|
"self": 620.4874629875703 |
|
}, |
|
"steps_from_proto": { |
|
"total": 27.70404500265431, |
|
"count": 64227, |
|
"is_parallel": true, |
|
"self": 6.591111103669391, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 21.11293389898492, |
|
"count": 513816, |
|
"is_parallel": true, |
|
"self": 21.11293389898492 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 508.1189118728216, |
|
"count": 64228, |
|
"self": 1.6844402537099086, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 95.22079032220063, |
|
"count": 64228, |
|
"self": 95.06898185019963, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1518084720009938, |
|
"count": 2, |
|
"self": 0.1518084720009938 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 411.2136812969111, |
|
"count": 457, |
|
"self": 174.7665951193194, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 236.4470861775917, |
|
"count": 22812, |
|
"self": 236.4470861775917 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 5.259935278445482e-07, |
|
"count": 1, |
|
"self": 5.259935278445482e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.06497997500991914, |
|
"count": 1, |
|
"self": 0.0007757390121696517, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.06420423599774949, |
|
"count": 1, |
|
"self": 0.06420423599774949 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |