socks22's picture
First Push
c55c207
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.7830238342285156,
"min": 2.7830238342285156,
"max": 2.865396022796631,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 28562.173828125,
"min": 28562.173828125,
"max": 29439.078125,
"count": 2
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.3469946384429932,
"min": 0.425903856754303,
"max": 1.3469946384429932,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 276.1339111328125,
"min": 82.62535095214844,
"max": 276.1339111328125,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06849076417628584,
"min": 0.06849076417628584,
"max": 0.07500171830197003,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3424538208814292,
"min": 0.3000068732078801,
"max": 0.3424538208814292,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19354043675988328,
"min": 0.13747005789157224,
"max": 0.19354043675988328,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9677021837994164,
"min": 0.549880231566289,
"max": 0.9677021837994164,
"count": 2
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032007656e-05,
"min": 7.032007656e-05,
"max": 0.00021882002706000002,
"count": 2
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0003516003828,
"min": 0.0003516003828,
"max": 0.0008752801082400001,
"count": 2
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.12344000000000002,
"min": 0.12344000000000002,
"max": 0.17294,
"count": 2
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.6172000000000001,
"min": 0.6172000000000001,
"max": 0.69176,
"count": 2
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0011796560000000003,
"min": 0.0011796560000000003,
"max": 0.003649706,
"count": 2
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.005898280000000001,
"min": 0.005898280000000001,
"max": 0.014598824,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 5.6909090909090905,
"min": 3.7045454545454546,
"max": 5.6909090909090905,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 313.0,
"min": 163.0,
"max": 313.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.6909090909090905,
"min": 3.7045454545454546,
"max": 5.6909090909090905,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 313.0,
"min": 163.0,
"max": 313.0,
"count": 2
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1704338548",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704338615"
},
"total": 66.749141678,
"count": 1,
"self": 0.4845906529999411,
"children": {
"run_training.setup": {
"total": 0.060601007000059326,
"count": 1,
"self": 0.060601007000059326
},
"TrainerController.start_learning": {
"total": 66.203950018,
"count": 1,
"self": 0.12077569699897595,
"children": {
"TrainerController._reset_env": {
"total": 3.54168486399999,
"count": 1,
"self": 3.54168486399999
},
"TrainerController.advance": {
"total": 62.408133616000896,
"count": 1868,
"self": 0.04392456400125866,
"children": {
"env_step": {
"total": 62.36420905199964,
"count": 1868,
"self": 40.94327603400018,
"children": {
"SubprocessEnvManager._take_step": {
"total": 21.3786817700003,
"count": 1868,
"self": 0.21728582599610036,
"children": {
"TorchPolicy.evaluate": {
"total": 21.161395944004198,
"count": 1868,
"self": 21.161395944004198
}
}
},
"workers": {
"total": 0.042251247999161023,
"count": 1868,
"self": 0.0,
"children": {
"worker_root": {
"total": 65.91379297500384,
"count": 1868,
"is_parallel": true,
"self": 33.46285452000109,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005630547000009756,
"count": 1,
"is_parallel": true,
"self": 0.004061634000208869,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015689129998008866,
"count": 10,
"is_parallel": true,
"self": 0.0015689129998008866
}
}
},
"UnityEnvironment.step": {
"total": 0.043205669000030866,
"count": 1,
"is_parallel": true,
"self": 0.0007374700001037127,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004892800000106945,
"count": 1,
"is_parallel": true,
"self": 0.0004892800000106945
},
"communicator.exchange": {
"total": 0.03932541399990441,
"count": 1,
"is_parallel": true,
"self": 0.03932541399990441
},
"steps_from_proto": {
"total": 0.0026535050000120464,
"count": 1,
"is_parallel": true,
"self": 0.000544021000223438,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021094839997886083,
"count": 10,
"is_parallel": true,
"self": 0.0021094839997886083
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 32.450938455002756,
"count": 1867,
"is_parallel": true,
"self": 1.4528985900013822,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.7713889480024818,
"count": 1867,
"is_parallel": true,
"self": 0.7713889480024818
},
"communicator.exchange": {
"total": 25.418061078001415,
"count": 1867,
"is_parallel": true,
"self": 25.418061078001415
},
"steps_from_proto": {
"total": 4.808589838997477,
"count": 1867,
"is_parallel": true,
"self": 0.9337597709932197,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.8748300680042576,
"count": 18670,
"is_parallel": true,
"self": 3.8748300680042576
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00043834300004164106,
"count": 1,
"self": 0.00043834300004164106,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 61.58453048200249,
"count": 93577,
"is_parallel": true,
"self": 2.0966589789838963,
"children": {
"process_trajectory": {
"total": 35.835639125018815,
"count": 93577,
"is_parallel": true,
"self": 35.835639125018815
},
"_update_policy": {
"total": 23.65223237799978,
"count": 9,
"is_parallel": true,
"self": 6.930589040001678,
"children": {
"TorchPPOOptimizer.update": {
"total": 16.721643337998103,
"count": 456,
"is_parallel": true,
"self": 16.721643337998103
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1329174980000971,
"count": 1,
"self": 0.0011299440001266703,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13178755399997044,
"count": 1,
"self": 0.13178755399997044
}
}
}
}
}
}
}