tcabgom's picture
First Push
75aac43 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.815469741821289,
"min": 2.815469741821289,
"max": 2.87460994720459,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 28957.10546875,
"min": 28957.10546875,
"max": 29502.12109375,
"count": 2
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.2821617126464844,
"min": 0.42765000462532043,
"max": 1.2821617126464844,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 262.8431396484375,
"min": 82.96410369873047,
"max": 262.8431396484375,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06825438676191968,
"min": 0.06825438676191968,
"max": 0.07196065745059363,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3412719338095984,
"min": 0.2878426298023745,
"max": 0.3412719338095984,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2024458503606273,
"min": 0.10372895898534826,
"max": 0.2024458503606273,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0122292518031364,
"min": 0.41491583594139303,
"max": 1.0122292518031364,
"count": 2
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032007656e-05,
"min": 7.032007656e-05,
"max": 0.00021882002706000002,
"count": 2
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0003516003828,
"min": 0.0003516003828,
"max": 0.0008752801082400001,
"count": 2
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.12344000000000002,
"min": 0.12344000000000002,
"max": 0.17294,
"count": 2
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.6172000000000001,
"min": 0.6172000000000001,
"max": 0.69176,
"count": 2
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0011796560000000003,
"min": 0.0011796560000000003,
"max": 0.003649706,
"count": 2
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.005898280000000001,
"min": 0.005898280000000001,
"max": 0.014598824,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 5.818181818181818,
"min": 2.909090909090909,
"max": 5.818181818181818,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 320.0,
"min": 128.0,
"max": 320.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.818181818181818,
"min": 2.909090909090909,
"max": 5.818181818181818,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 320.0,
"min": 128.0,
"max": 320.0,
"count": 2
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1725552130",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1725552198"
},
"total": 68.22342903899994,
"count": 1,
"self": 0.5937786979999373,
"children": {
"run_training.setup": {
"total": 0.10792317799996454,
"count": 1,
"self": 0.10792317799996454
},
"TrainerController.start_learning": {
"total": 67.52172716300004,
"count": 1,
"self": 0.12495731400224486,
"children": {
"TrainerController._reset_env": {
"total": 3.2610729369999945,
"count": 1,
"self": 3.2610729369999945
},
"TrainerController.advance": {
"total": 64.03587085599793,
"count": 1875,
"self": 0.04403221599523022,
"children": {
"env_step": {
"total": 63.9918386400027,
"count": 1875,
"self": 49.28247988799808,
"children": {
"SubprocessEnvManager._take_step": {
"total": 14.66775543500296,
"count": 1875,
"self": 0.26600483700258337,
"children": {
"TorchPolicy.evaluate": {
"total": 14.401750598000376,
"count": 1875,
"self": 14.401750598000376
}
}
},
"workers": {
"total": 0.04160331700165898,
"count": 1875,
"self": 0.0,
"children": {
"worker_root": {
"total": 67.27093235799714,
"count": 1875,
"is_parallel": true,
"self": 33.029041728997754,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005453470000020388,
"count": 1,
"is_parallel": true,
"self": 0.0016817969998328408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0037716730001875476,
"count": 10,
"is_parallel": true,
"self": 0.0037716730001875476
}
}
},
"UnityEnvironment.step": {
"total": 0.0516768579999507,
"count": 1,
"is_parallel": true,
"self": 0.0009856940000645409,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046061999989888136,
"count": 1,
"is_parallel": true,
"self": 0.00046061999989888136
},
"communicator.exchange": {
"total": 0.04774514400003227,
"count": 1,
"is_parallel": true,
"self": 0.04774514400003227
},
"steps_from_proto": {
"total": 0.002485399999955007,
"count": 1,
"is_parallel": true,
"self": 0.00047809399984544143,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020073060001095655,
"count": 10,
"is_parallel": true,
"self": 0.0020073060001095655
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 34.241890628999386,
"count": 1874,
"is_parallel": true,
"self": 1.619046524002897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.8137605769998117,
"count": 1874,
"is_parallel": true,
"self": 0.8137605769998117
},
"communicator.exchange": {
"total": 27.00445669899875,
"count": 1874,
"is_parallel": true,
"self": 27.00445669899875
},
"steps_from_proto": {
"total": 4.804626828997925,
"count": 1874,
"is_parallel": true,
"self": 0.9629585689975784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.841668260000347,
"count": 18740,
"is_parallel": true,
"self": 3.841668260000347
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0009113369999340648,
"count": 1,
"self": 0.0009113369999340648,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 63.3297814989794,
"count": 79578,
"is_parallel": true,
"self": 1.9165308339622698,
"children": {
"process_trajectory": {
"total": 35.83336801401708,
"count": 79578,
"is_parallel": true,
"self": 35.11303598901702,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7203320250000615,
"count": 4,
"is_parallel": true,
"self": 0.7203320250000615
}
}
},
"_update_policy": {
"total": 25.579882651000048,
"count": 9,
"is_parallel": true,
"self": 7.851575105000052,
"children": {
"TorchPPOOptimizer.update": {
"total": 17.728307545999996,
"count": 456,
"is_parallel": true,
"self": 17.728307545999996
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09891471899993576,
"count": 1,
"self": 0.002285051999933785,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09662966700000197,
"count": 1,
"self": 0.09662966700000197
}
}
}
}
}
}
}