mshibatatt's picture
first learning
c44a436
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8639993667602539,
"min": 0.8639993667602539,
"max": 2.854067802429199,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8249.4658203125,
"min": 8249.4658203125,
"max": 29228.5078125,
"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": 12.749567985534668,
"min": 0.3402627408504486,
"max": 12.749567985534668,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2486.165771484375,
"min": 66.01097106933594,
"max": 2573.82421875,
"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": 0.0649399194402104,
"min": 0.0649399194402104,
"max": 0.07399473763150893,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2597596777608416,
"min": 0.2597596777608416,
"max": 0.3695436106908007,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2045618623641192,
"min": 0.12705233039713337,
"max": 0.26742396722821626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8182474494564768,
"min": 0.5082093215885335,
"max": 1.3371198361410814,
"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": 25.40909090909091,
"min": 3.75,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 165.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.75,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 165.0,
"max": 1413.0,
"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": "1676441561",
"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": "1.21.6",
"end_time_seconds": "1676442023"
},
"total": 462.383358606,
"count": 1,
"self": 0.4883283650000294,
"children": {
"run_training.setup": {
"total": 0.21024075499997252,
"count": 1,
"self": 0.21024075499997252
},
"TrainerController.start_learning": {
"total": 461.684789486,
"count": 1,
"self": 0.5346868619913039,
"children": {
"TrainerController._reset_env": {
"total": 10.000716414999943,
"count": 1,
"self": 10.000716414999943
},
"TrainerController.advance": {
"total": 451.03238000700867,
"count": 18202,
"self": 0.276379900029724,
"children": {
"env_step": {
"total": 450.75600010697895,
"count": 18202,
"self": 310.55001077397833,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.94285845499746,
"count": 18202,
"self": 1.4409326069928738,
"children": {
"TorchPolicy.evaluate": {
"total": 138.5019258480046,
"count": 18202,
"self": 31.355784273000268,
"children": {
"TorchPolicy.sample_actions": {
"total": 107.14614157500432,
"count": 18202,
"self": 107.14614157500432
}
}
}
}
},
"workers": {
"total": 0.26313087800315316,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.1928613610022,
"count": 18202,
"is_parallel": true,
"self": 222.76422305800634,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006007510000017646,
"count": 1,
"is_parallel": true,
"self": 0.0034807539999519577,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025267560000656886,
"count": 10,
"is_parallel": true,
"self": 0.0025267560000656886
}
}
},
"UnityEnvironment.step": {
"total": 0.0344160169998986,
"count": 1,
"is_parallel": true,
"self": 0.0004740429998264517,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003833179999901404,
"count": 1,
"is_parallel": true,
"self": 0.0003833179999901404
},
"communicator.exchange": {
"total": 0.0313154890000078,
"count": 1,
"is_parallel": true,
"self": 0.0313154890000078
},
"steps_from_proto": {
"total": 0.0022431670000742088,
"count": 1,
"is_parallel": true,
"self": 0.0005911690001312309,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001651997999942978,
"count": 10,
"is_parallel": true,
"self": 0.001651997999942978
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.42863830299586,
"count": 18201,
"is_parallel": true,
"self": 9.447548379976865,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.094903938013999,
"count": 18201,
"is_parallel": true,
"self": 5.094903938013999
},
"communicator.exchange": {
"total": 192.4075050209965,
"count": 18201,
"is_parallel": true,
"self": 192.4075050209965
},
"steps_from_proto": {
"total": 30.478680964008504,
"count": 18201,
"is_parallel": true,
"self": 6.544576610008903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.9341043539996,
"count": 182010,
"is_parallel": true,
"self": 23.9341043539996
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001346470000953559,
"count": 1,
"self": 0.0001346470000953559,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.626473441921,
"count": 411119,
"is_parallel": true,
"self": 10.003380188959,
"children": {
"process_trajectory": {
"total": 256.24247714196383,
"count": 411119,
"is_parallel": true,
"self": 254.79408969796373,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4483874440001046,
"count": 4,
"is_parallel": true,
"self": 1.4483874440001046
}
}
},
"_update_policy": {
"total": 181.38061611099818,
"count": 90,
"is_parallel": true,
"self": 62.842047958992794,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.53856815200538,
"count": 4587,
"is_parallel": true,
"self": 118.53856815200538
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1168715549999888,
"count": 1,
"self": 0.0008883600000899605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11598319499989884,
"count": 1,
"self": 0.11598319499989884
}
}
}
}
}
}
}