ppo-Worm / run_logs /timers.json
vind's picture
Upload model
c2365e1
{
"name": "root",
"gauges": {
"Worm.Policy.Entropy.mean": {
"value": 1.411466360092163,
"min": 1.411466360092163,
"max": 1.4194236993789673,
"count": 15
},
"Worm.Policy.Entropy.sum": {
"value": 42343.9921875,
"min": 42343.9921875,
"max": 42582.7109375,
"count": 15
},
"Worm.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 15
},
"Worm.Environment.EpisodeLength.sum": {
"value": 29970.0,
"min": 29970.0,
"max": 29970.0,
"count": 15
},
"Worm.Step.mean": {
"value": 449000.0,
"min": 29000.0,
"max": 449000.0,
"count": 15
},
"Worm.Step.sum": {
"value": 449000.0,
"min": 29000.0,
"max": 449000.0,
"count": 15
},
"Worm.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.315215528011322,
"min": -0.0712854266166687,
"max": 0.315215528011322,
"count": 15
},
"Worm.Policy.ExtrinsicValueEstimate.sum": {
"value": 9.456465721130371,
"min": -2.067277431488037,
"max": 9.456465721130371,
"count": 15
},
"Worm.Environment.CumulativeReward.mean": {
"value": 5.783343554954627,
"min": 0.24587436616420746,
"max": 5.783343554954627,
"count": 15
},
"Worm.Environment.CumulativeReward.sum": {
"value": 173.5003066486388,
"min": 7.376230984926224,
"max": 173.5003066486388,
"count": 15
},
"Worm.Policy.ExtrinsicReward.mean": {
"value": 5.783343554954627,
"min": 0.24587436616420746,
"max": 5.783343554954627,
"count": 15
},
"Worm.Policy.ExtrinsicReward.sum": {
"value": 173.5003066486388,
"min": 7.376230984926224,
"max": 173.5003066486388,
"count": 15
},
"Worm.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
},
"Worm.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
},
"Worm.Losses.PolicyLoss.mean": {
"value": 0.01633231126054722,
"min": 0.012337169088173791,
"max": 0.01912836736023781,
"count": 14
},
"Worm.Losses.PolicyLoss.sum": {
"value": 0.01633231126054722,
"min": 0.012337169088173791,
"max": 0.01912836736023781,
"count": 14
},
"Worm.Losses.ValueLoss.mean": {
"value": 0.017203831113874912,
"min": 0.0008591748704756832,
"max": 0.017203831113874912,
"count": 14
},
"Worm.Losses.ValueLoss.sum": {
"value": 0.017203831113874912,
"min": 0.0008591748704756832,
"max": 0.017203831113874912,
"count": 14
},
"Worm.Policy.LearningRate.mean": {
"value": 0.000237000021,
"min": 0.000237000021,
"max": 0.00029550000149999997,
"count": 14
},
"Worm.Policy.LearningRate.sum": {
"value": 0.000237000021,
"min": 0.000237000021,
"max": 0.00029550000149999997,
"count": 14
},
"Worm.Policy.Epsilon.mean": {
"value": 0.17900000000000005,
"min": 0.17900000000000005,
"max": 0.19849999999999998,
"count": 14
},
"Worm.Policy.Epsilon.sum": {
"value": 0.17900000000000005,
"min": 0.17900000000000005,
"max": 0.19849999999999998,
"count": 14
},
"Worm.Policy.Beta.mean": {
"value": 0.003952100000000001,
"min": 0.003952100000000001,
"max": 0.004925149999999999,
"count": 14
},
"Worm.Policy.Beta.sum": {
"value": 0.003952100000000001,
"min": 0.003952100000000001,
"max": 0.004925149999999999,
"count": 14
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684746633",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=WormTrain1 --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": "1684747293"
},
"total": 659.9180999760001,
"count": 1,
"self": 0.07352231300046697,
"children": {
"run_training.setup": {
"total": 0.03818426799989538,
"count": 1,
"self": 0.03818426799989538
},
"TrainerController.start_learning": {
"total": 659.8063933949998,
"count": 1,
"self": 1.080842194138313,
"children": {
"TrainerController._reset_env": {
"total": 3.745757297999262,
"count": 1,
"self": 3.745757297999262
},
"TrainerController.advance": {
"total": 654.6150779138625,
"count": 45000,
"self": 1.049170173818311,
"children": {
"env_step": {
"total": 544.8430088800224,
"count": 45000,
"self": 478.02870215404164,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.17165337202641,
"count": 45000,
"self": 3.7014823060490016,
"children": {
"TorchPolicy.evaluate": {
"total": 62.47017106597741,
"count": 45000,
"self": 62.47017106597741
}
}
},
"workers": {
"total": 0.6426533539543016,
"count": 45000,
"self": 0.0,
"children": {
"worker_root": {
"total": 655.3147396391323,
"count": 45000,
"is_parallel": true,
"self": 244.27402511121,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009211650003635441,
"count": 1,
"is_parallel": true,
"self": 0.00026100900140590966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006601559989576344,
"count": 2,
"is_parallel": true,
"self": 0.0006601559989576344
}
}
},
"UnityEnvironment.step": {
"total": 0.033931656000277144,
"count": 1,
"is_parallel": true,
"self": 0.00027725200015993323,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005037299997638911,
"count": 1,
"is_parallel": true,
"self": 0.0005037299997638911
},
"communicator.exchange": {
"total": 0.0325767630001792,
"count": 1,
"is_parallel": true,
"self": 0.0325767630001792
},
"steps_from_proto": {
"total": 0.000573911000174121,
"count": 1,
"is_parallel": true,
"self": 0.0001916840001285891,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003822270000455319,
"count": 2,
"is_parallel": true,
"self": 0.0003822270000455319
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 411.0407145279223,
"count": 44999,
"is_parallel": true,
"self": 8.739806431796751,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 15.630739528060076,
"count": 44999,
"is_parallel": true,
"self": 15.630739528060076
},
"communicator.exchange": {
"total": 364.5179583861009,
"count": 44999,
"is_parallel": true,
"self": 364.5179583861009
},
"steps_from_proto": {
"total": 22.15221018196462,
"count": 44999,
"is_parallel": true,
"self": 8.000385195856325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 14.151824986108295,
"count": 89998,
"is_parallel": true,
"self": 14.151824986108295
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 108.72289886002181,
"count": 45000,
"self": 1.1560883401452884,
"children": {
"process_trajectory": {
"total": 21.401296547876882,
"count": 45000,
"self": 21.401296547876882
},
"_update_policy": {
"total": 86.16551397199964,
"count": 15,
"self": 73.76439783298156,
"children": {
"TorchPPOOptimizer.update": {
"total": 12.401116139018086,
"count": 602,
"self": 12.401116139018086
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4360002751345746e-06,
"count": 1,
"self": 1.4360002751345746e-06
},
"TrainerController._save_models": {
"total": 0.36471455299943045,
"count": 1,
"self": 0.0060506109994094,
"children": {
"RLTrainer._checkpoint": {
"total": 0.35866394200002105,
"count": 1,
"self": 0.35866394200002105
}
}
}
}
}
}
}