PPOPyramids / run_logs /timers.json
Bandika's picture
First training of Pyramids
ee9a408
raw
history blame
18.7 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2833195924758911,
"min": 0.2752564549446106,
"max": 1.415665864944458,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8540.3857421875,
"min": 8252.412109375,
"max": 42945.640625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989895.0,
"min": 29925.0,
"max": 989895.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989895.0,
"min": 29925.0,
"max": 989895.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.709172785282135,
"min": -0.08620855957269669,
"max": 0.7311785221099854,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 207.78762817382812,
"min": -20.690053939819336,
"max": 211.3105926513672,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.044210340827703476,
"min": -0.005935630761086941,
"max": 0.35764753818511963,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 12.953629493713379,
"min": -1.667912244796753,
"max": 84.76246643066406,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07236676250481053,
"min": 0.06376383846827212,
"max": 0.07236676250481053,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0131346750673473,
"min": 0.5058362820160966,
"max": 1.0800929795185963,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01695788236335246,
"min": 0.0012456460861304357,
"max": 0.017259233559004723,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23741035308693442,
"min": 0.011210814775173921,
"max": 0.2478796923127911,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.5900974700000024e-06,
"min": 7.5900974700000024e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010626136458000004,
"min": 0.00010626136458000004,
"max": 0.0036321319892893993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253000000000001,
"min": 0.10253000000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354200000000001,
"min": 1.3886848,
"max": 2.6624098000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002627470000000002,
"min": 0.0002627470000000002,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036784580000000025,
"min": 0.0036784580000000025,
"max": 0.12108998894,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013699849136173725,
"min": 0.013699849136173725,
"max": 0.6679756045341492,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1917978823184967,
"min": 0.1917978823184967,
"max": 4.6758294105529785,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 250.2016806722689,
"min": 250.2016806722689,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29774.0,
"min": 16852.0,
"max": 33248.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7168733129898708,
"min": -0.9999806972280625,
"max": 1.7217089104067003,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 206.02479755878448,
"min": -30.99940161406994,
"max": 206.02479755878448,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7168733129898708,
"min": -0.9999806972280625,
"max": 1.7217089104067003,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 206.02479755878448,
"min": -30.99940161406994,
"max": 206.02479755878448,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03507451241239323,
"min": 0.03507451241239323,
"max": 14.123379903681139,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.208941489487188,
"min": 4.208941489487188,
"max": 240.09745836257935,
"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": "1681575231",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "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": "1681577693"
},
"total": 2462.1884065840004,
"count": 1,
"self": 0.9343986010003391,
"children": {
"run_training.setup": {
"total": 0.21669870600004515,
"count": 1,
"self": 0.21669870600004515
},
"TrainerController.start_learning": {
"total": 2461.037309277,
"count": 1,
"self": 1.6988317510367779,
"children": {
"TrainerController._reset_env": {
"total": 6.08676486600001,
"count": 1,
"self": 6.08676486600001
},
"TrainerController.advance": {
"total": 2453.103410819963,
"count": 64299,
"self": 1.8272569439632207,
"children": {
"env_step": {
"total": 1782.2859144829686,
"count": 64299,
"self": 1655.208425818925,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.01031287804352,
"count": 64299,
"self": 5.553534097076067,
"children": {
"TorchPolicy.evaluate": {
"total": 120.45677878096745,
"count": 62551,
"self": 120.45677878096745
}
}
},
"workers": {
"total": 1.067175786000007,
"count": 64299,
"self": 0.0,
"children": {
"worker_root": {
"total": 2454.8203040000335,
"count": 64299,
"is_parallel": true,
"self": 932.842774966035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005959663999988152,
"count": 1,
"is_parallel": true,
"self": 0.004008257999942089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019514060000460631,
"count": 8,
"is_parallel": true,
"self": 0.0019514060000460631
}
}
},
"UnityEnvironment.step": {
"total": 0.09911872199995742,
"count": 1,
"is_parallel": true,
"self": 0.0006210299999338531,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005450710000332037,
"count": 1,
"is_parallel": true,
"self": 0.0005450710000332037
},
"communicator.exchange": {
"total": 0.09083355799998571,
"count": 1,
"is_parallel": true,
"self": 0.09083355799998571
},
"steps_from_proto": {
"total": 0.007119063000004644,
"count": 1,
"is_parallel": true,
"self": 0.004360741000027701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027583219999769426,
"count": 8,
"is_parallel": true,
"self": 0.0027583219999769426
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1521.9775290339985,
"count": 64298,
"is_parallel": true,
"self": 35.975584927027285,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.461910043003797,
"count": 64298,
"is_parallel": true,
"self": 26.461910043003797
},
"communicator.exchange": {
"total": 1350.3523880889602,
"count": 64298,
"is_parallel": true,
"self": 1350.3523880889602
},
"steps_from_proto": {
"total": 109.18764597500711,
"count": 64298,
"is_parallel": true,
"self": 24.152054740102017,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.0355912349051,
"count": 514384,
"is_parallel": true,
"self": 85.0355912349051
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 668.990239393031,
"count": 64299,
"self": 3.247761524983048,
"children": {
"process_trajectory": {
"total": 122.33210543204541,
"count": 64299,
"self": 122.0481149360453,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28399049600011494,
"count": 2,
"self": 0.28399049600011494
}
}
},
"_update_policy": {
"total": 543.4103724360025,
"count": 453,
"self": 347.83896163900295,
"children": {
"TorchPPOOptimizer.update": {
"total": 195.57141079699954,
"count": 22803,
"self": 195.57141079699954
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2730001799354795e-06,
"count": 1,
"self": 1.2730001799354795e-06
},
"TrainerController._save_models": {
"total": 0.14830056700020577,
"count": 1,
"self": 0.0020976129999326076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14620295400027317,
"count": 1,
"self": 0.14620295400027317
}
}
}
}
}
}
}