ppo-Huggy / run_logs /timers.json
APLunch's picture
Huggy
e402f74 verified
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407135248184204,
"min": 1.407135248184204,
"max": 1.4287010431289673,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68775.140625,
"min": 68008.90625,
"max": 76001.828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 111.68018018018019,
"min": 94.69598470363289,
"max": 384.412213740458,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49586.0,
"min": 48845.0,
"max": 50358.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999936.0,
"min": 49770.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999936.0,
"min": 49770.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.26306414604187,
"min": 0.04771837964653969,
"max": 2.3801422119140625,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1004.8004760742188,
"min": 6.2033891677856445,
"max": 1195.0140380859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.428196563645526,
"min": 1.8118828324171212,
"max": 3.980776226229784,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1522.1192742586136,
"min": 235.54476821422577,
"max": 1904.523760855198,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.428196563645526,
"min": 1.8118828324171212,
"max": 3.980776226229784,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1522.1192742586136,
"min": 235.54476821422577,
"max": 1904.523760855198,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01640070970491555,
"min": 0.012570574564354803,
"max": 0.019669667359266896,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0328014194098311,
"min": 0.025141149128709607,
"max": 0.05852662659308407,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04422592222690583,
"min": 0.02362694265320897,
"max": 0.05667869516958793,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08845184445381166,
"min": 0.04725388530641794,
"max": 0.15367907360196115,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.197098601000002e-06,
"min": 4.197098601000002e-06,
"max": 0.00029529990156670005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.394197202000004e-06,
"min": 8.394197202000004e-06,
"max": 0.0008440080186640001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10139900000000002,
"min": 0.10139900000000002,
"max": 0.1984333,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20279800000000003,
"min": 0.20279800000000003,
"max": 0.5813360000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.98101e-05,
"min": 7.98101e-05,
"max": 0.00492182167,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001596202,
"min": 0.0001596202,
"max": 0.014068666400000002,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713122829",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713125422"
},
"total": 2592.7150532289997,
"count": 1,
"self": 0.7873480650000602,
"children": {
"run_training.setup": {
"total": 0.0811676440000042,
"count": 1,
"self": 0.0811676440000042
},
"TrainerController.start_learning": {
"total": 2591.84653752,
"count": 1,
"self": 4.6813333490067635,
"children": {
"TrainerController._reset_env": {
"total": 3.0129489049999734,
"count": 1,
"self": 3.0129489049999734
},
"TrainerController.advance": {
"total": 2583.9828102859933,
"count": 230899,
"self": 4.9071356828976604,
"children": {
"env_step": {
"total": 2098.690885571007,
"count": 230899,
"self": 1743.1834308579205,
"children": {
"SubprocessEnvManager._take_step": {
"total": 352.3881395561042,
"count": 230899,
"self": 18.939767413131506,
"children": {
"TorchPolicy.evaluate": {
"total": 333.4483721429727,
"count": 222898,
"self": 333.4483721429727
}
}
},
"workers": {
"total": 3.1193151569823385,
"count": 230899,
"self": 0.0,
"children": {
"worker_root": {
"total": 2583.747102628059,
"count": 230899,
"is_parallel": true,
"self": 1176.3347937580465,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009538310000039019,
"count": 1,
"is_parallel": true,
"self": 0.0002546149999602676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006992160000436343,
"count": 2,
"is_parallel": true,
"self": 0.0006992160000436343
}
}
},
"UnityEnvironment.step": {
"total": 0.03158286300003965,
"count": 1,
"is_parallel": true,
"self": 0.00041978000001563487,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023367699998289027,
"count": 1,
"is_parallel": true,
"self": 0.00023367699998289027
},
"communicator.exchange": {
"total": 0.030134422999992694,
"count": 1,
"is_parallel": true,
"self": 0.030134422999992694
},
"steps_from_proto": {
"total": 0.0007949830000484326,
"count": 1,
"is_parallel": true,
"self": 0.000230695000027481,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005642880000209516,
"count": 2,
"is_parallel": true,
"self": 0.0005642880000209516
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1407.4123088700126,
"count": 230898,
"is_parallel": true,
"self": 41.25392930795624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.27958630495726,
"count": 230898,
"is_parallel": true,
"self": 93.27958630495726
},
"communicator.exchange": {
"total": 1173.517219048042,
"count": 230898,
"is_parallel": true,
"self": 1173.517219048042
},
"steps_from_proto": {
"total": 99.36157420905698,
"count": 230898,
"is_parallel": true,
"self": 38.483923510052364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.87765069900462,
"count": 461796,
"is_parallel": true,
"self": 60.87765069900462
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 480.38478903208875,
"count": 230899,
"self": 7.0840899121503185,
"children": {
"process_trajectory": {
"total": 159.70771598293703,
"count": 230899,
"self": 158.2954926859365,
"children": {
"RLTrainer._checkpoint": {
"total": 1.412223297000537,
"count": 10,
"self": 1.412223297000537
}
}
},
"_update_policy": {
"total": 313.5929831370014,
"count": 96,
"self": 251.1408174999961,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.452165637005294,
"count": 2880,
"self": 62.452165637005294
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5069999790284783e-06,
"count": 1,
"self": 1.5069999790284783e-06
},
"TrainerController._save_models": {
"total": 0.1694434729997738,
"count": 1,
"self": 0.0029512559999602672,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16649221699981354,
"count": 1,
"self": 0.16649221699981354
}
}
}
}
}
}
}