hasarinduperera's picture
First Push
1882303
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9028462767601013,
"min": 0.9028462767601013,
"max": 2.862602949142456,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8620.3759765625,
"min": 8620.3759765625,
"max": 29315.91796875,
"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": 12.901559829711914,
"min": 0.27302220463752747,
"max": 12.901559829711914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2515.80419921875,
"min": 52.96630859375,
"max": 2622.031494140625,
"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": 0.0738809776802929,
"min": 0.061916231817974454,
"max": 0.07578347378868391,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2955239107211716,
"min": 0.25995474568124194,
"max": 0.3789173689434196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2098892778888637,
"min": 0.11096842867760537,
"max": 0.2995877940865124,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8395571115554548,
"min": 0.4438737147104215,
"max": 1.4156236353458143,
"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": 25.386363636363637,
"min": 3.1136363636363638,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 137.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.1136363636363638,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 137.0,
"max": 1389.0,
"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": "1678061811",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678062281"
},
"total": 470.29205542299997,
"count": 1,
"self": 0.4316240609999795,
"children": {
"run_training.setup": {
"total": 0.11020544399997334,
"count": 1,
"self": 0.11020544399997334
},
"TrainerController.start_learning": {
"total": 469.750225918,
"count": 1,
"self": 0.5329545760030783,
"children": {
"TrainerController._reset_env": {
"total": 9.273664472000007,
"count": 1,
"self": 9.273664472000007
},
"TrainerController.advance": {
"total": 459.815808866997,
"count": 18201,
"self": 0.2851706749932532,
"children": {
"env_step": {
"total": 459.5306381920037,
"count": 18201,
"self": 316.31901859701145,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.9371195359917,
"count": 18201,
"self": 1.5502192149959342,
"children": {
"TorchPolicy.evaluate": {
"total": 141.38690032099578,
"count": 18201,
"self": 31.947362700994574,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.4395376200012,
"count": 18201,
"self": 109.4395376200012
}
}
}
}
},
"workers": {
"total": 0.27450005900055885,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.2065737969949,
"count": 18201,
"is_parallel": true,
"self": 227.4954878519885,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00746341200004963,
"count": 1,
"is_parallel": true,
"self": 0.003931678999947508,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003531733000102122,
"count": 10,
"is_parallel": true,
"self": 0.003531733000102122
}
}
},
"UnityEnvironment.step": {
"total": 0.11936312400001725,
"count": 1,
"is_parallel": true,
"self": 0.0006975100000090606,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000470534999976735,
"count": 1,
"is_parallel": true,
"self": 0.000470534999976735
},
"communicator.exchange": {
"total": 0.11554524900003571,
"count": 1,
"is_parallel": true,
"self": 0.11554524900003571
},
"steps_from_proto": {
"total": 0.0026498299999957453,
"count": 1,
"is_parallel": true,
"self": 0.0008156679999729022,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018341620000228431,
"count": 10,
"is_parallel": true,
"self": 0.0018341620000228431
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.7110859450064,
"count": 18200,
"is_parallel": true,
"self": 9.524171865013386,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.488758524994864,
"count": 18200,
"is_parallel": true,
"self": 5.488758524994864
},
"communicator.exchange": {
"total": 193.22046250400388,
"count": 18200,
"is_parallel": true,
"self": 193.22046250400388
},
"steps_from_proto": {
"total": 32.477693050994276,
"count": 18200,
"is_parallel": true,
"self": 7.161379560982198,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.316313490012078,
"count": 182000,
"is_parallel": true,
"self": 25.316313490012078
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001725759999544607,
"count": 1,
"self": 0.0001725759999544607,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 456.3744016130102,
"count": 406524,
"is_parallel": true,
"self": 10.319816789059189,
"children": {
"process_trajectory": {
"total": 262.9360474969511,
"count": 406524,
"is_parallel": true,
"self": 262.19015417895116,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7458933179999576,
"count": 4,
"is_parallel": true,
"self": 0.7458933179999576
}
}
},
"_update_policy": {
"total": 183.1185373269999,
"count": 90,
"is_parallel": true,
"self": 63.85823403700027,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.26030328999963,
"count": 4584,
"is_parallel": true,
"self": 119.26030328999963
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12762542699999813,
"count": 1,
"self": 0.0008979599999747734,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12672746700002335,
"count": 1,
"self": 0.12672746700002335
}
}
}
}
}
}
}