carolinainmymind's picture
First Push
6b3dd8e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8896161317825317,
"min": 0.884853184223175,
"max": 2.873835802078247,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8523.412109375,
"min": 8523.412109375,
"max": 29557.40234375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.856908798217773,
"min": 0.39039674401283264,
"max": 12.869176864624023,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.09716796875,
"min": 75.73696899414062,
"max": 2625.31201171875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06830870068469998,
"min": 0.061968510254861456,
"max": 0.07524129776090073,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2732348027387999,
"min": 0.24787404101944582,
"max": 0.37620648880450364,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20691998624334149,
"min": 0.12658961546634706,
"max": 0.28603453197899986,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8276799449733659,
"min": 0.5063584618653882,
"max": 1.4301726598949993,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.045454545454547,
"min": 3.2045454545454546,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 141.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.2045454545454546,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 141.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681127011",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1681127455"
},
"total": 443.485372452,
"count": 1,
"self": 0.6417079840000497,
"children": {
"run_training.setup": {
"total": 0.11517317099998081,
"count": 1,
"self": 0.11517317099998081
},
"TrainerController.start_learning": {
"total": 442.72849129699995,
"count": 1,
"self": 0.5444466919998945,
"children": {
"TrainerController._reset_env": {
"total": 3.858903730999998,
"count": 1,
"self": 3.858903730999998
},
"TrainerController.advance": {
"total": 438.115448717,
"count": 18216,
"self": 0.2735251170058177,
"children": {
"env_step": {
"total": 437.8419235999942,
"count": 18216,
"self": 321.58863473799164,
"children": {
"SubprocessEnvManager._take_step": {
"total": 115.99232887100447,
"count": 18216,
"self": 1.7240185639980155,
"children": {
"TorchPolicy.evaluate": {
"total": 114.26831030700646,
"count": 18216,
"self": 114.26831030700646
}
}
},
"workers": {
"total": 0.2609599909980602,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.19606791500433,
"count": 18216,
"is_parallel": true,
"self": 202.55350060999297,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050591830000144,
"count": 1,
"is_parallel": true,
"self": 0.0035121999999319087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015469830000824913,
"count": 10,
"is_parallel": true,
"self": 0.0015469830000824913
}
}
},
"UnityEnvironment.step": {
"total": 0.034083107000014934,
"count": 1,
"is_parallel": true,
"self": 0.0005722780000496641,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030942299997605005,
"count": 1,
"is_parallel": true,
"self": 0.00030942299997605005
},
"communicator.exchange": {
"total": 0.03137776099998746,
"count": 1,
"is_parallel": true,
"self": 0.03137776099998746
},
"steps_from_proto": {
"total": 0.0018236450000017612,
"count": 1,
"is_parallel": true,
"self": 0.00039603499999429914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001427610000007462,
"count": 10,
"is_parallel": true,
"self": 0.001427610000007462
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.64256730501137,
"count": 18215,
"is_parallel": true,
"self": 9.579175476996625,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.278676430007238,
"count": 18215,
"is_parallel": true,
"self": 5.278676430007238
},
"communicator.exchange": {
"total": 193.152134841997,
"count": 18215,
"is_parallel": true,
"self": 193.152134841997
},
"steps_from_proto": {
"total": 30.63258055601051,
"count": 18215,
"is_parallel": true,
"self": 6.015204870995319,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.61737568501519,
"count": 182150,
"is_parallel": true,
"self": 24.61737568501519
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016318200005116523,
"count": 1,
"self": 0.00016318200005116523,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.84821890399587,
"count": 387685,
"is_parallel": true,
"self": 9.346803877000582,
"children": {
"process_trajectory": {
"total": 238.8859324949953,
"count": 387685,
"is_parallel": true,
"self": 237.30089509099543,
"children": {
"RLTrainer._checkpoint": {
"total": 1.585037403999877,
"count": 4,
"is_parallel": true,
"self": 1.585037403999877
}
}
},
"_update_policy": {
"total": 186.615482532,
"count": 90,
"is_parallel": true,
"self": 68.36984766400292,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.24563486799707,
"count": 4584,
"is_parallel": true,
"self": 118.24563486799707
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.209528975000012,
"count": 1,
"self": 0.0010936940000192408,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20843528099999276,
"count": 1,
"self": 0.20843528099999276
}
}
}
}
}
}
}