ppo-Huggy / run_logs /timers.json
Orion181's picture
Huggy
dbc019a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4084752798080444,
"min": 1.4084752798080444,
"max": 1.430112600326538,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68322.3203125,
"min": 68322.3203125,
"max": 76401.0625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.9460966542751,
"min": 89.42857142857143,
"max": 403.7903225806452,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49467.0,
"min": 49242.0,
"max": 50070.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999934.0,
"min": 49699.0,
"max": 1999934.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999934.0,
"min": 49699.0,
"max": 1999934.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2575411796569824,
"min": 0.1439306139945984,
"max": 2.4464292526245117,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1214.55712890625,
"min": 17.703466415405273,
"max": 1288.9384765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.355226649670796,
"min": 1.901137964027684,
"max": 3.958784897263649,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1805.1119375228882,
"min": 233.83996957540512,
"max": 2046.9012413024902,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.355226649670796,
"min": 1.901137964027684,
"max": 3.958784897263649,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1805.1119375228882,
"min": 233.83996957540512,
"max": 2046.9012413024902,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013906277958853429,
"min": 0.012733780779429556,
"max": 0.019765110408964878,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.041718833876560286,
"min": 0.02546756155885911,
"max": 0.05779095569159835,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04847833116849264,
"min": 0.021551016500840584,
"max": 0.055214451832903765,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14543499350547792,
"min": 0.04310203300168117,
"max": 0.1656433554987113,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4189488603833296e-06,
"min": 3.4189488603833296e-06,
"max": 0.000295337176554275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0256846581149988e-05,
"min": 1.0256846581149988e-05,
"max": 0.0008439478686840499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113961666666671,
"min": 0.10113961666666671,
"max": 0.19844572500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30341885000000013,
"min": 0.20743274999999994,
"max": 0.5813159500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.68668716666666e-05,
"min": 6.68668716666666e-05,
"max": 0.0049224416775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020060061499999982,
"min": 0.00020060061499999982,
"max": 0.014067665904999999,
"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": "1728921521",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728924090"
},
"total": 2569.161309427,
"count": 1,
"self": 0.4338965640004062,
"children": {
"run_training.setup": {
"total": 0.05399218600007316,
"count": 1,
"self": 0.05399218600007316
},
"TrainerController.start_learning": {
"total": 2568.6734206769997,
"count": 1,
"self": 4.535369173963318,
"children": {
"TrainerController._reset_env": {
"total": 3.008566824000013,
"count": 1,
"self": 3.008566824000013
},
"TrainerController.advance": {
"total": 2561.012546687037,
"count": 231457,
"self": 4.725509471971236,
"children": {
"env_step": {
"total": 2033.3973770099983,
"count": 231457,
"self": 1606.6993601109812,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.79239281100627,
"count": 231457,
"self": 15.962497318955116,
"children": {
"TorchPolicy.evaluate": {
"total": 407.82989549205115,
"count": 222847,
"self": 407.82989549205115
}
}
},
"workers": {
"total": 2.9056240880109954,
"count": 231457,
"self": 0.0,
"children": {
"worker_root": {
"total": 2561.291744423027,
"count": 231457,
"is_parallel": true,
"self": 1262.7789447260104,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010301500000196029,
"count": 1,
"is_parallel": true,
"self": 0.0002968769999824872,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007332730000371157,
"count": 2,
"is_parallel": true,
"self": 0.0007332730000371157
}
}
},
"UnityEnvironment.step": {
"total": 0.030155059999970035,
"count": 1,
"is_parallel": true,
"self": 0.000355836999915482,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018531900002471957,
"count": 1,
"is_parallel": true,
"self": 0.00018531900002471957
},
"communicator.exchange": {
"total": 0.0288747780000449,
"count": 1,
"is_parallel": true,
"self": 0.0288747780000449
},
"steps_from_proto": {
"total": 0.0007391259999849353,
"count": 1,
"is_parallel": true,
"self": 0.00019257399992511637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000546552000059819,
"count": 2,
"is_parallel": true,
"self": 0.000546552000059819
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1298.5127996970166,
"count": 231456,
"is_parallel": true,
"self": 38.59868029103791,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.73934401696192,
"count": 231456,
"is_parallel": true,
"self": 84.73934401696192
},
"communicator.exchange": {
"total": 1082.5790158860386,
"count": 231456,
"is_parallel": true,
"self": 1082.5790158860386
},
"steps_from_proto": {
"total": 92.59575950297813,
"count": 231456,
"is_parallel": true,
"self": 34.84315577490031,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.752603728077816,
"count": 462912,
"is_parallel": true,
"self": 57.752603728077816
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 522.889660205067,
"count": 231457,
"self": 6.906343302022265,
"children": {
"process_trajectory": {
"total": 166.7896480200452,
"count": 231457,
"self": 165.42554311304502,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3641049070001827,
"count": 10,
"self": 1.3641049070001827
}
}
},
"_update_policy": {
"total": 349.19366888299953,
"count": 97,
"self": 281.12280212899645,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.07086675400308,
"count": 2910,
"self": 68.07086675400308
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0459998520673253e-06,
"count": 1,
"self": 1.0459998520673253e-06
},
"TrainerController._save_models": {
"total": 0.11693694599989612,
"count": 1,
"self": 0.001977026999611553,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11495991900028457,
"count": 1,
"self": 0.11495991900028457
}
}
}
}
}
}
}