Sukmin's picture
First Push
bb5dd32
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0321390628814697,
"min": 1.0321390628814697,
"max": 2.8696365356445312,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9888.923828125,
"min": 9888.923828125,
"max": 29451.080078125,
"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": 13.038034439086914,
"min": 0.23317871987819672,
"max": 13.038034439086914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2542.416748046875,
"min": 45.236671447753906,
"max": 2644.447509765625,
"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": 0.06841824773836575,
"min": 0.06440806140379601,
"max": 0.07882012423243734,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.273672990953463,
"min": 0.2622485226607287,
"max": 0.3786748566857497,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19786763658710554,
"min": 0.13876620806552764,
"max": 0.26427724641912126,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7914705463484222,
"min": 0.5550648322621106,
"max": 1.3213862320956062,
"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": 25.318181818181817,
"min": 3.7954545454545454,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 167.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.7954545454545454,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 167.0,
"max": 1426.0,
"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": "1688969098",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "1688969575"
},
"total": 477.07034440000007,
"count": 1,
"self": 0.7808053820000964,
"children": {
"run_training.setup": {
"total": 0.044036380000022746,
"count": 1,
"self": 0.044036380000022746
},
"TrainerController.start_learning": {
"total": 476.24550263799995,
"count": 1,
"self": 0.5615521149996994,
"children": {
"TrainerController._reset_env": {
"total": 4.209529616999987,
"count": 1,
"self": 4.209529616999987
},
"TrainerController.advance": {
"total": 471.2463052380003,
"count": 18215,
"self": 0.2671932090024143,
"children": {
"env_step": {
"total": 470.97911202899786,
"count": 18215,
"self": 343.3389343479962,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.37140194000239,
"count": 18215,
"self": 1.8796546649962806,
"children": {
"TorchPolicy.evaluate": {
"total": 125.4917472750061,
"count": 18215,
"self": 125.4917472750061
}
}
},
"workers": {
"total": 0.26877574099927415,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.36504773999434,
"count": 18215,
"is_parallel": true,
"self": 220.9157957269934,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050687799999877825,
"count": 1,
"is_parallel": true,
"self": 0.003615267000043332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014535129999444507,
"count": 10,
"is_parallel": true,
"self": 0.0014535129999444507
}
}
},
"UnityEnvironment.step": {
"total": 0.035100639000006595,
"count": 1,
"is_parallel": true,
"self": 0.0005952749999664775,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040095000002793313,
"count": 1,
"is_parallel": true,
"self": 0.00040095000002793313
},
"communicator.exchange": {
"total": 0.03199944300001789,
"count": 1,
"is_parallel": true,
"self": 0.03199944300001789
},
"steps_from_proto": {
"total": 0.0021049709999942934,
"count": 1,
"is_parallel": true,
"self": 0.0004839139999148756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016210570000794178,
"count": 10,
"is_parallel": true,
"self": 0.0016210570000794178
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.44925201300094,
"count": 18214,
"is_parallel": true,
"self": 10.635075560002349,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.360462562997782,
"count": 18214,
"is_parallel": true,
"self": 5.360462562997782
},
"communicator.exchange": {
"total": 201.14516544799937,
"count": 18214,
"is_parallel": true,
"self": 201.14516544799937
},
"steps_from_proto": {
"total": 36.30854844200144,
"count": 18214,
"is_parallel": true,
"self": 6.526073522014087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.78247491998735,
"count": 182140,
"is_parallel": true,
"self": 29.78247491998735
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017663699998138327,
"count": 1,
"self": 0.00017663699998138327,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 467.58173253102933,
"count": 461679,
"is_parallel": true,
"self": 9.99512078804787,
"children": {
"process_trajectory": {
"total": 255.54773031398145,
"count": 461679,
"is_parallel": true,
"self": 253.86924042098155,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6784898929998917,
"count": 4,
"is_parallel": true,
"self": 1.6784898929998917
}
}
},
"_update_policy": {
"total": 202.038881429,
"count": 90,
"is_parallel": true,
"self": 79.63077224299792,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.4081091860021,
"count": 4587,
"is_parallel": true,
"self": 122.4081091860021
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22793903100000534,
"count": 1,
"self": 0.0012084190000223316,
"children": {
"RLTrainer._checkpoint": {
"total": 0.226730611999983,
"count": 1,
"self": 0.226730611999983
}
}
}
}
}
}
}