kobybibas's picture
First Push
8fd4f55 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.8528919219970703,
"min": 2.8528919219970703,
"max": 2.8528919219970703,
"count": 1
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 29122.3203125,
"min": 29122.3203125,
"max": 29122.3203125,
"count": 1
},
"SnowballTarget.Step.mean": {
"value": 9952.0,
"min": 9952.0,
"max": 9952.0,
"count": 1
},
"SnowballTarget.Step.sum": {
"value": 9952.0,
"min": 9952.0,
"max": 9952.0,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.28102564811706543,
"min": 0.28102564811706543,
"max": 0.28102564811706543,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 54.51897430419922,
"min": 54.51897430419922,
"max": 54.51897430419922,
"count": 1
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06820122829427133,
"min": 0.06820122829427133,
"max": 0.06820122829427133,
"count": 1
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27280491317708533,
"min": 0.27280491317708533,
"max": 0.27280491317708533,
"count": 1
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.12313998790740895,
"min": 0.12313998790740895,
"max": 0.12313998790740895,
"count": 1
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.4925599516296358,
"min": 0.4925599516296358,
"max": 0.4925599516296358,
"count": 1
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.000291882002706,
"min": 0.000291882002706,
"max": 0.000291882002706,
"count": 1
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.001167528010824,
"min": 0.001167528010824,
"max": 0.001167528010824,
"count": 1
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.19729400000000002,
"min": 0.19729400000000002,
"max": 0.19729400000000002,
"count": 1
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.7891760000000001,
"min": 0.7891760000000001,
"max": 0.7891760000000001,
"count": 1
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0048649706,
"min": 0.0048649706,
"max": 0.0048649706,
"count": 1
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0194598824,
"min": 0.0194598824,
"max": 0.0194598824,
"count": 1
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 1
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 8756.0,
"count": 1
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 3.6136363636363638,
"min": 3.6136363636363638,
"max": 3.6136363636363638,
"count": 1
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 159.0,
"min": 159.0,
"max": 159.0,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 3.6136363636363638,
"min": 3.6136363636363638,
"max": 3.6136363636363638,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 159.0,
"min": 159.0,
"max": 159.0,
"count": 1
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1752301186",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752301216"
},
"total": 29.38090735799983,
"count": 1,
"self": 0.35320694200004255,
"children": {
"run_training.setup": {
"total": 0.01969141899985516,
"count": 1,
"self": 0.01969141899985516
},
"TrainerController.start_learning": {
"total": 29.008008996999934,
"count": 1,
"self": 0.02153817900421018,
"children": {
"TrainerController._reset_env": {
"total": 1.9241610300000502,
"count": 1,
"self": 1.9241610300000502
},
"TrainerController.advance": {
"total": 26.708078227995657,
"count": 1192,
"self": 0.024127501990733435,
"children": {
"env_step": {
"total": 20.011934316000634,
"count": 1192,
"self": 15.319462741004827,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4.679613707996168,
"count": 1192,
"self": 0.08122205799486437,
"children": {
"TorchPolicy.evaluate": {
"total": 4.598391650001304,
"count": 1192,
"self": 4.598391650001304
}
}
},
"workers": {
"total": 0.012857866999638645,
"count": 1192,
"self": 0.0,
"children": {
"worker_root": {
"total": 28.387564327998234,
"count": 1192,
"is_parallel": true,
"self": 14.955522612998038,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022545069998614053,
"count": 1,
"is_parallel": true,
"self": 0.0006766740000330174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001577832999828388,
"count": 10,
"is_parallel": true,
"self": 0.001577832999828388
}
}
},
"UnityEnvironment.step": {
"total": 0.06362026100009643,
"count": 1,
"is_parallel": true,
"self": 0.000580893999995169,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003952270001263969,
"count": 1,
"is_parallel": true,
"self": 0.0003952270001263969
},
"communicator.exchange": {
"total": 0.06060817399998086,
"count": 1,
"is_parallel": true,
"self": 0.06060817399998086
},
"steps_from_proto": {
"total": 0.002035965999994005,
"count": 1,
"is_parallel": true,
"self": 0.0004025300002012955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016334359997927095,
"count": 10,
"is_parallel": true,
"self": 0.0016334359997927095
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 13.432041715000196,
"count": 1191,
"is_parallel": true,
"self": 0.6321662390116671,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.35890731699737444,
"count": 1191,
"is_parallel": true,
"self": 0.35890731699737444
},
"communicator.exchange": {
"total": 10.381565965999926,
"count": 1191,
"is_parallel": true,
"self": 10.381565965999926
},
"steps_from_proto": {
"total": 2.0594021929912287,
"count": 1191,
"is_parallel": true,
"self": 0.3660063199763499,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1.6933958730148788,
"count": 11910,
"is_parallel": true,
"self": 1.6933958730148788
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 6.672016410004289,
"count": 1192,
"self": 0.025580198004263366,
"children": {
"process_trajectory": {
"total": 1.5893441820001044,
"count": 1192,
"self": 1.5893441820001044
},
"_update_policy": {
"total": 5.057092029999922,
"count": 6,
"self": 2.097092116001477,
"children": {
"TorchPPOOptimizer.update": {
"total": 2.9599999139984448,
"count": 252,
"self": 2.9599999139984448
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2969999261258636e-06,
"count": 1,
"self": 1.2969999261258636e-06
},
"TrainerController._save_models": {
"total": 0.3542302630000904,
"count": 1,
"self": 0.000971471999946516,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3532587910001439,
"count": 1,
"self": 0.3532587910001439
}
}
}
}
}
}
}