hruslen's picture
First Training of Snowball Agent in Colab
9868afe
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9960113167762756,
"min": 0.9960113167762756,
"max": 2.8661324977874756,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9509.916015625,
"min": 9509.916015625,
"max": 29352.0625,
"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": 12.46843433380127,
"min": 0.25636786222457886,
"max": 12.46843433380127,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2431.3447265625,
"min": 49.7353630065918,
"max": 2522.3466796875,
"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": 0.06505586078321143,
"min": 0.06240625446399802,
"max": 0.07520252638260704,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26022344313284573,
"min": 0.25224413470120866,
"max": 0.3760126319130352,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20856383092263167,
"min": 0.10463500609986631,
"max": 0.29284846151576327,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8342553236905267,
"min": 0.41854002439946525,
"max": 1.4642423075788162,
"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": 24.772727272727273,
"min": 2.909090909090909,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 128.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 2.909090909090909,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 128.0,
"max": 1375.0,
"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": "1681745602",
"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": "1681746055"
},
"total": 453.341502793,
"count": 1,
"self": 0.39257914099994196,
"children": {
"run_training.setup": {
"total": 0.10857407499997862,
"count": 1,
"self": 0.10857407499997862
},
"TrainerController.start_learning": {
"total": 452.8403495770001,
"count": 1,
"self": 0.5207404450068225,
"children": {
"TrainerController._reset_env": {
"total": 5.089145108000139,
"count": 1,
"self": 5.089145108000139
},
"TrainerController.advance": {
"total": 447.10203511899294,
"count": 18203,
"self": 0.2613833209989025,
"children": {
"env_step": {
"total": 446.84065179799404,
"count": 18203,
"self": 330.33324437601914,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.24964563598542,
"count": 18203,
"self": 1.7264723449738995,
"children": {
"TorchPolicy.evaluate": {
"total": 114.52317329101152,
"count": 18203,
"self": 114.52317329101152
}
}
},
"workers": {
"total": 0.2577617859894872,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 451.3236478280014,
"count": 18203,
"is_parallel": true,
"self": 209.84684391899714,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009003300999893327,
"count": 1,
"is_parallel": true,
"self": 0.005102879000105531,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0039004219997877954,
"count": 10,
"is_parallel": true,
"self": 0.0039004219997877954
}
}
},
"UnityEnvironment.step": {
"total": 0.0706482819998655,
"count": 1,
"is_parallel": true,
"self": 0.0006644980001055956,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043608800001493364,
"count": 1,
"is_parallel": true,
"self": 0.00043608800001493364
},
"communicator.exchange": {
"total": 0.06695884199984903,
"count": 1,
"is_parallel": true,
"self": 0.06695884199984903
},
"steps_from_proto": {
"total": 0.002588853999895946,
"count": 1,
"is_parallel": true,
"self": 0.0005050510001183284,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020838029997776175,
"count": 10,
"is_parallel": true,
"self": 0.0020838029997776175
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.47680390900427,
"count": 18202,
"is_parallel": true,
"self": 10.017122931010135,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.344777840995903,
"count": 18202,
"is_parallel": true,
"self": 5.344777840995903
},
"communicator.exchange": {
"total": 194.82089430200585,
"count": 18202,
"is_parallel": true,
"self": 194.82089430200585
},
"steps_from_proto": {
"total": 31.294008834992383,
"count": 18202,
"is_parallel": true,
"self": 6.142981240008339,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.151027594984043,
"count": 182020,
"is_parallel": true,
"self": 25.151027594984043
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014950100012356415,
"count": 1,
"self": 0.00014950100012356415,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.768907518014,
"count": 391191,
"is_parallel": true,
"self": 9.721570114005544,
"children": {
"process_trajectory": {
"total": 241.95447723100665,
"count": 391191,
"is_parallel": true,
"self": 241.0957785820067,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8586986489999617,
"count": 4,
"is_parallel": true,
"self": 0.8586986489999617
}
}
},
"_update_policy": {
"total": 192.09286017300178,
"count": 90,
"is_parallel": true,
"self": 75.09119635898924,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.00166381401255,
"count": 4587,
"is_parallel": true,
"self": 117.00166381401255
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1282794040000681,
"count": 1,
"self": 0.000840687000163598,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1274387169999045,
"count": 1,
"self": 0.1274387169999045
}
}
}
}
}
}
}