michal512's picture
First Snowball
f91daaf
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8008137345314026,
"min": 0.8008137345314026,
"max": 2.863649606704712,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7734.25927734375,
"min": 7633.6708984375,
"max": 29326.634765625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.66077995300293,
"min": 0.27493128180503845,
"max": 13.717352867126465,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2800.4599609375,
"min": 53.336669921875,
"max": 2800.4599609375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07370806241090702,
"min": 0.0628397108956158,
"max": 0.07696056700525314,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3685403120545351,
"min": 0.2573007822821976,
"max": 0.36953805502550907,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19188887900581547,
"min": 0.11048335276598878,
"max": 0.2936715156424279,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9594443950290773,
"min": 0.4419334110639551,
"max": 1.417667936489051,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.654545454545456,
"min": 3.022727272727273,
"max": 26.88888888888889,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1466.0,
"min": 133.0,
"max": 1473.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.654545454545456,
"min": 3.022727272727273,
"max": 26.88888888888889,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1466.0,
"min": 133.0,
"max": 1473.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676552746",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1676553853"
},
"total": 1106.313400595,
"count": 1,
"self": 0.6060751249999612,
"children": {
"run_training.setup": {
"total": 0.12442119000002094,
"count": 1,
"self": 0.12442119000002094
},
"TrainerController.start_learning": {
"total": 1105.58290428,
"count": 1,
"self": 1.2481981370158337,
"children": {
"TrainerController._reset_env": {
"total": 9.548535236999896,
"count": 1,
"self": 9.548535236999896
},
"TrainerController.advance": {
"total": 1094.6042025399845,
"count": 45477,
"self": 0.6746689249705469,
"children": {
"env_step": {
"total": 1093.929533615014,
"count": 45477,
"self": 751.8646620280207,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.4215945589981,
"count": 45477,
"self": 3.5832763809885364,
"children": {
"TorchPolicy.evaluate": {
"total": 337.83831817800956,
"count": 45477,
"self": 74.72432161200311,
"children": {
"TorchPolicy.sample_actions": {
"total": 263.11399656600645,
"count": 45477,
"self": 263.11399656600645
}
}
}
}
},
"workers": {
"total": 0.6432770279951683,
"count": 45477,
"self": 0.0,
"children": {
"worker_root": {
"total": 1101.998732232032,
"count": 45477,
"is_parallel": true,
"self": 528.0602709630462,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009825927999941086,
"count": 1,
"is_parallel": true,
"self": 0.004248411999810742,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005577516000130345,
"count": 10,
"is_parallel": true,
"self": 0.005577516000130345
}
}
},
"UnityEnvironment.step": {
"total": 0.04643582000005608,
"count": 1,
"is_parallel": true,
"self": 0.0005514890001450112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040405899994766514,
"count": 1,
"is_parallel": true,
"self": 0.00040405899994766514
},
"communicator.exchange": {
"total": 0.04343961600000057,
"count": 1,
"is_parallel": true,
"self": 0.04343961600000057
},
"steps_from_proto": {
"total": 0.002040655999962837,
"count": 1,
"is_parallel": true,
"self": 0.00043248499991932476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016081710000435123,
"count": 10,
"is_parallel": true,
"self": 0.0016081710000435123
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 573.9384612689857,
"count": 45476,
"is_parallel": true,
"self": 23.448107296991452,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.432237521975026,
"count": 45476,
"is_parallel": true,
"self": 12.432237521975026
},
"communicator.exchange": {
"total": 462.44685847600886,
"count": 45476,
"is_parallel": true,
"self": 462.44685847600886
},
"steps_from_proto": {
"total": 75.61125797401041,
"count": 45476,
"is_parallel": true,
"self": 16.29466357300987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.31659440100054,
"count": 454760,
"is_parallel": true,
"self": 59.31659440100054
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.118699985156127e-05,
"count": 1,
"self": 4.118699985156127e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1086.3986154089284,
"count": 983529,
"is_parallel": true,
"self": 24.555108428020276,
"children": {
"process_trajectory": {
"total": 620.6725686159089,
"count": 983529,
"is_parallel": true,
"self": 618.7079962279088,
"children": {
"RLTrainer._checkpoint": {
"total": 1.9645723880000787,
"count": 10,
"is_parallel": true,
"self": 1.9645723880000787
}
}
},
"_update_policy": {
"total": 441.1709383649993,
"count": 227,
"is_parallel": true,
"self": 153.87889822200634,
"children": {
"TorchPPOOptimizer.update": {
"total": 287.29204014299296,
"count": 11574,
"is_parallel": true,
"self": 287.29204014299296
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.18192717900001298,
"count": 1,
"self": 0.0012557279999327875,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1806714510000802,
"count": 1,
"self": 0.1806714510000802
}
}
}
}
}
}
}