ppo-Huggy / run_logs /timers.json
dhinman's picture
Huggy
5a81fb9
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.40034019947052,
"min": 1.40034019947052,
"max": 1.4252753257751465,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68415.0234375,
"min": 67204.78125,
"max": 78763.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.74131944444444,
"min": 72.99851851851852,
"max": 393.453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49387.0,
"min": 49237.0,
"max": 50362.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49810.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49810.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5068466663360596,
"min": 0.14389866590499878,
"max": 2.5456156730651855,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1443.9437255859375,
"min": 18.275131225585938,
"max": 1718.29052734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.856806776796778,
"min": 1.7404886988673622,
"max": 4.027192264927758,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2221.520703434944,
"min": 221.042064756155,
"max": 2718.3547788262367,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.856806776796778,
"min": 1.7404886988673622,
"max": 4.027192264927758,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2221.520703434944,
"min": 221.042064756155,
"max": 2718.3547788262367,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01701446282119529,
"min": 0.014144906062817122,
"max": 0.02001861856373984,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05104338846358587,
"min": 0.028289812125634244,
"max": 0.060055855691219524,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056387307536270886,
"min": 0.022772352738926808,
"max": 0.06565585546195507,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16916192260881266,
"min": 0.045544705477853616,
"max": 0.1768339604139328,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.401898866066665e-06,
"min": 3.401898866066665e-06,
"max": 0.000295333876555375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0205696598199996e-05,
"min": 1.0205696598199996e-05,
"max": 0.0008437539187487,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113393333333336,
"min": 0.10113393333333336,
"max": 0.198444625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30340180000000005,
"min": 0.20744050000000003,
"max": 0.5812513,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.658327333333333e-05,
"min": 6.658327333333333e-05,
"max": 0.0049223867875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019974981999999996,
"min": 0.00019974981999999996,
"max": 0.014064439869999999,
"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": "1689504090",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1689506470"
},
"total": 2379.5742842199998,
"count": 1,
"self": 0.7440522779993444,
"children": {
"run_training.setup": {
"total": 0.04134685700000773,
"count": 1,
"self": 0.04134685700000773
},
"TrainerController.start_learning": {
"total": 2378.7888850850004,
"count": 1,
"self": 4.272822912890206,
"children": {
"TrainerController._reset_env": {
"total": 4.965105292999965,
"count": 1,
"self": 4.965105292999965
},
"TrainerController.advance": {
"total": 2369.3749673261104,
"count": 233324,
"self": 4.427962635984841,
"children": {
"env_step": {
"total": 1833.0063741180466,
"count": 233324,
"self": 1544.7597122420284,
"children": {
"SubprocessEnvManager._take_step": {
"total": 285.4868257719644,
"count": 233324,
"self": 16.694628836891525,
"children": {
"TorchPolicy.evaluate": {
"total": 268.79219693507287,
"count": 222936,
"self": 268.79219693507287
}
}
},
"workers": {
"total": 2.759836104053875,
"count": 233324,
"self": 0.0,
"children": {
"worker_root": {
"total": 2371.070888075974,
"count": 233324,
"is_parallel": true,
"self": 1110.4615518729288,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009206629999880533,
"count": 1,
"is_parallel": true,
"self": 0.00028097699998852477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006396859999995286,
"count": 2,
"is_parallel": true,
"self": 0.0006396859999995286
}
}
},
"UnityEnvironment.step": {
"total": 0.04821763599989026,
"count": 1,
"is_parallel": true,
"self": 0.000342689999911272,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022322000006624876,
"count": 1,
"is_parallel": true,
"self": 0.00022322000006624876
},
"communicator.exchange": {
"total": 0.04684371899998041,
"count": 1,
"is_parallel": true,
"self": 0.04684371899998041
},
"steps_from_proto": {
"total": 0.0008080069999323314,
"count": 1,
"is_parallel": true,
"self": 0.00020899399987683864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005990130000554927,
"count": 2,
"is_parallel": true,
"self": 0.0005990130000554927
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.6093362030451,
"count": 233323,
"is_parallel": true,
"self": 39.441117228033136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.28732288198239,
"count": 233323,
"is_parallel": true,
"self": 80.28732288198239
},
"communicator.exchange": {
"total": 1044.6332723549826,
"count": 233323,
"is_parallel": true,
"self": 1044.6332723549826
},
"steps_from_proto": {
"total": 96.24762373804697,
"count": 233323,
"is_parallel": true,
"self": 33.84327160602152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.40435213202545,
"count": 466646,
"is_parallel": true,
"self": 62.40435213202545
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 531.9406305720792,
"count": 233324,
"self": 6.388783300048203,
"children": {
"process_trajectory": {
"total": 139.4228100010315,
"count": 233324,
"self": 137.91792690703198,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5048830939995241,
"count": 10,
"self": 1.5048830939995241
}
}
},
"_update_policy": {
"total": 386.12903727099945,
"count": 97,
"self": 325.79890349900074,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.3301337719987,
"count": 2910,
"self": 60.3301337719987
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.258999873243738e-06,
"count": 1,
"self": 1.258999873243738e-06
},
"TrainerController._save_models": {
"total": 0.17598829400003524,
"count": 1,
"self": 0.002716308999879402,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17327198500015584,
"count": 1,
"self": 0.17327198500015584
}
}
}
}
}
}
}