bitcloud2's picture
Upload trained ppo angent
36a60b2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0063018798828125,
"min": 1.0063018798828125,
"max": 2.857790946960449,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9608.1708984375,
"min": 9608.1708984375,
"max": 29266.63671875,
"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": 13.439315795898438,
"min": 0.47020071744918823,
"max": 13.439315795898438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2620.66650390625,
"min": 91.21894073486328,
"max": 2711.219482421875,
"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": 0.13836354653003405,
"min": 0.13175596367961107,
"max": 0.1455018940202124,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.5534541861201362,
"min": 0.5534541861201362,
"max": 0.7092838196553843,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17535534228526933,
"min": 0.12953608018784402,
"max": 0.2783466178613404,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7014213691410773,
"min": 0.5181443207513761,
"max": 1.3042053178171902,
"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": 0.0013851600382799997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102694,
"min": 0.102694,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410776,
"min": 0.410776,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.431818181818183,
"min": 3.727272727272727,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1163.0,
"min": 164.0,
"max": 1436.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.431818181818183,
"min": 3.727272727272727,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1163.0,
"min": 164.0,
"max": 1436.0,
"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": "1673395104",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673395704"
},
"total": 600.733118973,
"count": 1,
"self": 0.4404205320000756,
"children": {
"run_training.setup": {
"total": 0.12126013199997487,
"count": 1,
"self": 0.12126013199997487
},
"TrainerController.start_learning": {
"total": 600.171438309,
"count": 1,
"self": 0.6050551869926721,
"children": {
"TrainerController._reset_env": {
"total": 8.967333245999953,
"count": 1,
"self": 8.967333245999953
},
"TrainerController.advance": {
"total": 590.4544367290074,
"count": 18202,
"self": 0.31375321100688325,
"children": {
"env_step": {
"total": 590.1406835180005,
"count": 18202,
"self": 445.6064294219974,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.22187278200437,
"count": 18202,
"self": 1.578735267007005,
"children": {
"TorchPolicy.evaluate": {
"total": 142.64313751499736,
"count": 18202,
"self": 31.342083540998487,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.30105397399888,
"count": 18202,
"self": 111.30105397399888
}
}
}
}
},
"workers": {
"total": 0.3123813139987419,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 598.7013946480014,
"count": 18202,
"is_parallel": true,
"self": 346.1336997910112,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008026971999981924,
"count": 1,
"is_parallel": true,
"self": 0.003724728000122468,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004302243999859456,
"count": 10,
"is_parallel": true,
"self": 0.004302243999859456
}
}
},
"UnityEnvironment.step": {
"total": 0.0374735039999905,
"count": 1,
"is_parallel": true,
"self": 0.0005699310000295554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046596199996429277,
"count": 1,
"is_parallel": true,
"self": 0.00046596199996429277
},
"communicator.exchange": {
"total": 0.03422109799998907,
"count": 1,
"is_parallel": true,
"self": 0.03422109799998907
},
"steps_from_proto": {
"total": 0.0022165130000075806,
"count": 1,
"is_parallel": true,
"self": 0.0005527990000473437,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016637139999602368,
"count": 10,
"is_parallel": true,
"self": 0.0016637139999602368
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.56769485699016,
"count": 18201,
"is_parallel": true,
"self": 9.469293750007864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.801835235994474,
"count": 18201,
"is_parallel": true,
"self": 5.801835235994474
},
"communicator.exchange": {
"total": 200.73138071499199,
"count": 18201,
"is_parallel": true,
"self": 200.73138071499199
},
"steps_from_proto": {
"total": 36.565185155995835,
"count": 18201,
"is_parallel": true,
"self": 8.04439568797676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.520789468019075,
"count": 182010,
"is_parallel": true,
"self": 28.520789468019075
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.9816999990071054e-05,
"count": 1,
"self": 4.9816999990071054e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 586.753571165977,
"count": 386480,
"is_parallel": true,
"self": 11.391186213009519,
"children": {
"process_trajectory": {
"total": 273.92919910096697,
"count": 386480,
"is_parallel": true,
"self": 273.0740527089669,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8551463920000515,
"count": 4,
"is_parallel": true,
"self": 0.8551463920000515
}
}
},
"_update_policy": {
"total": 301.4331858520004,
"count": 90,
"is_parallel": true,
"self": 49.54788466999389,
"children": {
"TorchPPOOptimizer.update": {
"total": 251.88530118200651,
"count": 18354,
"is_parallel": true,
"self": 251.88530118200651
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14456332999998267,
"count": 1,
"self": 0.0010978469999827212,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14346548299999995,
"count": 1,
"self": 0.14346548299999995
}
}
}
}
}
}
}