SAL83's picture
First Push
f4426df
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9586253762245178,
"min": 0.9586253762245178,
"max": 2.8641905784606934,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9174.044921875,
"min": 9174.044921875,
"max": 29458.19921875,
"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": 12.535113334655762,
"min": 0.40824639797210693,
"max": 12.535113334655762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2444.34716796875,
"min": 79.19979858398438,
"max": 2528.007080078125,
"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": 0.07109583027982701,
"min": 0.0625584123580826,
"max": 0.07943687640320551,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28438332111930803,
"min": 0.2509329643930245,
"max": 0.37091977750499017,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1906367755111526,
"min": 0.11833749829412565,
"max": 0.2810586610845491,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7625471020446104,
"min": 0.4733499931765026,
"max": 1.4052933054227454,
"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": 25.15909090909091,
"min": 3.227272727272727,
"max": 25.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 142.0,
"max": 1362.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.227272727272727,
"max": 25.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 142.0,
"max": 1362.0,
"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": "1679525516",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679526072"
},
"total": 556.3675121939999,
"count": 1,
"self": 0.5403598019998981,
"children": {
"run_training.setup": {
"total": 0.12868620200003988,
"count": 1,
"self": 0.12868620200003988
},
"TrainerController.start_learning": {
"total": 555.69846619,
"count": 1,
"self": 0.8103461139945694,
"children": {
"TrainerController._reset_env": {
"total": 6.397031453000011,
"count": 1,
"self": 6.397031453000011
},
"TrainerController.advance": {
"total": 548.3384897810056,
"count": 18203,
"self": 0.4381099980129193,
"children": {
"env_step": {
"total": 547.9003797829927,
"count": 18203,
"self": 441.1587867260058,
"children": {
"SubprocessEnvManager._take_step": {
"total": 106.3423087139982,
"count": 18203,
"self": 2.9713236019977103,
"children": {
"TorchPolicy.evaluate": {
"total": 103.37098511200048,
"count": 18203,
"self": 103.37098511200048
}
}
},
"workers": {
"total": 0.3992843429886648,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 553.6396466209958,
"count": 18203,
"is_parallel": true,
"self": 241.0167414939919,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006098663999978271,
"count": 1,
"is_parallel": true,
"self": 0.004389518999857955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017091450001203157,
"count": 10,
"is_parallel": true,
"self": 0.0017091450001203157
}
}
},
"UnityEnvironment.step": {
"total": 0.12214803599999868,
"count": 1,
"is_parallel": true,
"self": 0.0009339129999261786,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041699300004438555,
"count": 1,
"is_parallel": true,
"self": 0.00041699300004438555
},
"communicator.exchange": {
"total": 0.11830476300002601,
"count": 1,
"is_parallel": true,
"self": 0.11830476300002601
},
"steps_from_proto": {
"total": 0.0024923670000021048,
"count": 1,
"is_parallel": true,
"self": 0.0004958299999202609,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001996537000081844,
"count": 10,
"is_parallel": true,
"self": 0.001996537000081844
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 312.6229051270039,
"count": 18202,
"is_parallel": true,
"self": 12.152512487016566,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.7239914739964775,
"count": 18202,
"is_parallel": true,
"self": 6.7239914739964775
},
"communicator.exchange": {
"total": 251.98683416400172,
"count": 18202,
"is_parallel": true,
"self": 251.98683416400172
},
"steps_from_proto": {
"total": 41.759567001989126,
"count": 18202,
"is_parallel": true,
"self": 8.643355341986478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.11621166000265,
"count": 182020,
"is_parallel": true,
"self": 33.11621166000265
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00023582399990118574,
"count": 1,
"self": 0.00023582399990118574,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 543.0088442899482,
"count": 629411,
"is_parallel": true,
"self": 15.056491731946608,
"children": {
"process_trajectory": {
"total": 297.823841005001,
"count": 629411,
"is_parallel": true,
"self": 296.538491940001,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2853490649999912,
"count": 4,
"is_parallel": true,
"self": 1.2853490649999912
}
}
},
"_update_policy": {
"total": 230.12851155300058,
"count": 90,
"is_parallel": true,
"self": 82.81866688699984,
"children": {
"TorchPPOOptimizer.update": {
"total": 147.30984466600074,
"count": 4587,
"is_parallel": true,
"self": 147.30984466600074
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15236301799996,
"count": 1,
"self": 0.0012170079999123118,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15114601000004768,
"count": 1,
"self": 0.15114601000004768
}
}
}
}
}
}
}