gan11's picture
First Push
b68d704
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9634349346160889,
"min": 0.9634349346160889,
"max": 2.871608018875122,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9209.474609375,
"min": 9209.474609375,
"max": 29439.724609375,
"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": 12.71196460723877,
"min": 0.33023354411125183,
"max": 12.71196460723877,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2478.8330078125,
"min": 64.0653076171875,
"max": 2552.95068359375,
"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": 0.06397761808572493,
"min": 0.06397761808572493,
"max": 0.07408873204148417,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2559104723428997,
"min": 0.2559104723428997,
"max": 0.37044366020742087,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1956045512913489,
"min": 0.12055253396586825,
"max": 0.2766575879033874,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7824182051653956,
"min": 0.482210135863473,
"max": 1.3373890522063947,
"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": 25.09090909090909,
"min": 3.159090909090909,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 139.0,
"max": 1366.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 3.159090909090909,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 139.0,
"max": 1366.0,
"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": "1684201352",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684201855"
},
"total": 502.7665164900001,
"count": 1,
"self": 0.4386910750000652,
"children": {
"run_training.setup": {
"total": 0.04667998699994769,
"count": 1,
"self": 0.04667998699994769
},
"TrainerController.start_learning": {
"total": 502.28114542800006,
"count": 1,
"self": 0.5724970580085937,
"children": {
"TrainerController._reset_env": {
"total": 3.878006685999935,
"count": 1,
"self": 3.878006685999935
},
"TrainerController.advance": {
"total": 497.6777387679914,
"count": 18202,
"self": 0.2836348789726344,
"children": {
"env_step": {
"total": 497.39410388901877,
"count": 18202,
"self": 362.2549471000194,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.84263335199375,
"count": 18202,
"self": 1.8818608289900567,
"children": {
"TorchPolicy.evaluate": {
"total": 132.9607725230037,
"count": 18202,
"self": 132.9607725230037
}
}
},
"workers": {
"total": 0.2965234370055896,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 500.49105394798767,
"count": 18202,
"is_parallel": true,
"self": 235.61962517298196,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0066729640000176005,
"count": 1,
"is_parallel": true,
"self": 0.00520427600019957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014686879998180302,
"count": 10,
"is_parallel": true,
"self": 0.0014686879998180302
}
}
},
"UnityEnvironment.step": {
"total": 0.052076895000027434,
"count": 1,
"is_parallel": true,
"self": 0.0005031820001022425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004011620000028415,
"count": 1,
"is_parallel": true,
"self": 0.0004011620000028415
},
"communicator.exchange": {
"total": 0.04922967599998174,
"count": 1,
"is_parallel": true,
"self": 0.04922967599998174
},
"steps_from_proto": {
"total": 0.0019428749999406136,
"count": 1,
"is_parallel": true,
"self": 0.0004211950000581055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015216799998825081,
"count": 10,
"is_parallel": true,
"self": 0.0015216799998825081
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 264.8714287750057,
"count": 18201,
"is_parallel": true,
"self": 10.456706175016961,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.815965397996365,
"count": 18201,
"is_parallel": true,
"self": 5.815965397996365
},
"communicator.exchange": {
"total": 211.25327690599408,
"count": 18201,
"is_parallel": true,
"self": 211.25327690599408
},
"steps_from_proto": {
"total": 37.3454802959983,
"count": 18201,
"is_parallel": true,
"self": 7.222996568997473,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.122483727000827,
"count": 182010,
"is_parallel": true,
"self": 30.122483727000827
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017938500013769954,
"count": 1,
"self": 0.00017938500013769954,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 493.5166428670243,
"count": 473462,
"is_parallel": true,
"self": 11.523354607009878,
"children": {
"process_trajectory": {
"total": 270.304660097014,
"count": 473462,
"is_parallel": true,
"self": 269.45120406601404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8534560309999506,
"count": 4,
"is_parallel": true,
"self": 0.8534560309999506
}
}
},
"_update_policy": {
"total": 211.68862816300043,
"count": 90,
"is_parallel": true,
"self": 81.07579806799697,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.61283009500346,
"count": 4584,
"is_parallel": true,
"self": 130.61283009500346
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15272353099999236,
"count": 1,
"self": 0.0009851150000486086,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15173841599994375,
"count": 1,
"self": 0.15173841599994375
}
}
}
}
}
}
}