aymenkhs's picture
First version solving using ppo
7045eec
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9103318452835083,
"min": 0.9103318452835083,
"max": 2.858489751815796,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8681.8349609375,
"min": 8681.8349609375,
"max": 29273.79296875,
"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": 12.889375686645508,
"min": 0.3523203134536743,
"max": 12.889375686645508,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2513.42822265625,
"min": 68.35014343261719,
"max": 2609.634765625,
"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": 0.06728599678985227,
"min": 0.063078381498738,
"max": 0.07576264935184963,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26914398715940907,
"min": 0.2602564853244557,
"max": 0.37881324675924816,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20731524297711898,
"min": 0.11852709150087892,
"max": 0.28139296356661647,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8292609719084759,
"min": 0.4741083660035157,
"max": 1.3623054617760226,
"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": 25.886363636363637,
"min": 3.5681818181818183,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1139.0,
"min": 157.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.886363636363637,
"min": 3.5681818181818183,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1139.0,
"min": 157.0,
"max": 1402.0,
"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": "1679676910",
"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": "1679677368"
},
"total": 458.475348185,
"count": 1,
"self": 0.43756453899999315,
"children": {
"run_training.setup": {
"total": 0.10581976100002066,
"count": 1,
"self": 0.10581976100002066
},
"TrainerController.start_learning": {
"total": 457.93196388499996,
"count": 1,
"self": 0.5162573499973178,
"children": {
"TrainerController._reset_env": {
"total": 9.862670237999964,
"count": 1,
"self": 9.862670237999964
},
"TrainerController.advance": {
"total": 447.42383478500267,
"count": 18202,
"self": 0.27579365300067593,
"children": {
"env_step": {
"total": 447.148041132002,
"count": 18202,
"self": 327.0541298000025,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.84186801001061,
"count": 18202,
"self": 2.378117039017752,
"children": {
"TorchPolicy.evaluate": {
"total": 117.46375097099286,
"count": 18202,
"self": 117.46375097099286
}
}
},
"workers": {
"total": 0.2520433219888787,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.5895149100022,
"count": 18202,
"is_parallel": true,
"self": 219.9841254670024,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006012655999995786,
"count": 1,
"is_parallel": true,
"self": 0.004354342000112865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001658313999882921,
"count": 10,
"is_parallel": true,
"self": 0.001658313999882921
}
}
},
"UnityEnvironment.step": {
"total": 0.09713167799998246,
"count": 1,
"is_parallel": true,
"self": 0.0005466990000400074,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038886999999476757,
"count": 1,
"is_parallel": true,
"self": 0.00038886999999476757
},
"communicator.exchange": {
"total": 0.09432026899997936,
"count": 1,
"is_parallel": true,
"self": 0.09432026899997936
},
"steps_from_proto": {
"total": 0.0018758399999683206,
"count": 1,
"is_parallel": true,
"self": 0.0003742770001053941,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015015629998629265,
"count": 10,
"is_parallel": true,
"self": 0.0015015629998629265
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.6053894429998,
"count": 18201,
"is_parallel": true,
"self": 9.318231124973636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.088313245017275,
"count": 18201,
"is_parallel": true,
"self": 5.088313245017275
},
"communicator.exchange": {
"total": 192.20257833301093,
"count": 18201,
"is_parallel": true,
"self": 192.20257833301093
},
"steps_from_proto": {
"total": 29.996266739997964,
"count": 18201,
"is_parallel": true,
"self": 5.790939224022111,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.205327515975853,
"count": 182010,
"is_parallel": true,
"self": 24.205327515975853
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011782700005369406,
"count": 1,
"self": 0.00011782700005369406,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 444.3236048250113,
"count": 375048,
"is_parallel": true,
"self": 9.354120351058327,
"children": {
"process_trajectory": {
"total": 244.9535021489528,
"count": 375048,
"is_parallel": true,
"self": 244.19919580795283,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7543063409999604,
"count": 4,
"is_parallel": true,
"self": 0.7543063409999604
}
}
},
"_update_policy": {
"total": 190.01598232500015,
"count": 90,
"is_parallel": true,
"self": 74.10963938800262,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.90634293699753,
"count": 4587,
"is_parallel": true,
"self": 115.90634293699753
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12908368499995504,
"count": 1,
"self": 0.0008787780000147905,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12820490699994025,
"count": 1,
"self": 0.12820490699994025
}
}
}
}
}
}
}