fx1H's picture
First Push
94b98c8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.7895750999450684,
"min": 2.7895750999450684,
"max": 2.8708066940307617,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 28660.09375,
"min": 28660.09375,
"max": 29463.087890625,
"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": 1.3478578329086304,
"min": 0.40442225337028503,
"max": 1.3478578329086304,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 276.31085205078125,
"min": 78.45791625976562,
"max": 276.31085205078125,
"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": 0.06652786807526889,
"min": 0.06652786807526889,
"max": 0.06803328180185596,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.33263934037634446,
"min": 0.27213312720742383,
"max": 0.33263934037634446,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18513441912683787,
"min": 0.1090575416124992,
"max": 0.18513441912683787,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9256720956341894,
"min": 0.4362301664499968,
"max": 0.9256720956341894,
"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": 5.763636363636364,
"min": 3.25,
"max": 5.763636363636364,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 317.0,
"min": 143.0,
"max": 317.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.763636363636364,
"min": 3.25,
"max": 5.763636363636364,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 317.0,
"min": 143.0,
"max": 317.0,
"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": "1687461706",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687461760"
},
"total": 54.33024887500005,
"count": 1,
"self": 0.3863301220001176,
"children": {
"run_training.setup": {
"total": 0.06603377299995827,
"count": 1,
"self": 0.06603377299995827
},
"TrainerController.start_learning": {
"total": 53.877884979999976,
"count": 1,
"self": 0.07233218900171323,
"children": {
"TrainerController._reset_env": {
"total": 4.921087909999983,
"count": 1,
"self": 4.921087909999983
},
"TrainerController.advance": {
"total": 48.74915394299842,
"count": 1873,
"self": 0.028461743001003015,
"children": {
"env_step": {
"total": 48.720692199997416,
"count": 1873,
"self": 36.17217834400185,
"children": {
"SubprocessEnvManager._take_step": {
"total": 12.521627183994724,
"count": 1873,
"self": 0.16274781999447896,
"children": {
"TorchPolicy.evaluate": {
"total": 12.358879364000245,
"count": 1873,
"self": 12.358879364000245
}
}
},
"workers": {
"total": 0.026886672000841827,
"count": 1873,
"self": 0.0,
"children": {
"worker_root": {
"total": 53.656848492001586,
"count": 1873,
"is_parallel": true,
"self": 28.095002653000506,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008589515000039682,
"count": 1,
"is_parallel": true,
"self": 0.006323667999822646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002265847000217036,
"count": 10,
"is_parallel": true,
"self": 0.002265847000217036
}
}
},
"UnityEnvironment.step": {
"total": 0.04746153199994296,
"count": 1,
"is_parallel": true,
"self": 0.0007010759999275251,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033874999996896804,
"count": 1,
"is_parallel": true,
"self": 0.00033874999996896804
},
"communicator.exchange": {
"total": 0.04444131299999299,
"count": 1,
"is_parallel": true,
"self": 0.04444131299999299
},
"steps_from_proto": {
"total": 0.001980393000053482,
"count": 1,
"is_parallel": true,
"self": 0.0003465949998826545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016337980001708274,
"count": 10,
"is_parallel": true,
"self": 0.0016337980001708274
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 25.56184583900108,
"count": 1872,
"is_parallel": true,
"self": 1.1036952069989638,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.5350873730014882,
"count": 1872,
"is_parallel": true,
"self": 0.5350873730014882
},
"communicator.exchange": {
"total": 20.394926337000584,
"count": 1872,
"is_parallel": true,
"self": 20.394926337000584
},
"steps_from_proto": {
"total": 3.5281369220000443,
"count": 1872,
"is_parallel": true,
"self": 0.6486376429961638,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.8794992790038805,
"count": 18720,
"is_parallel": true,
"self": 2.8794992790038805
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020146299993939465,
"count": 1,
"self": 0.00020146299993939465,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 48.41818968300106,
"count": 44530,
"is_parallel": true,
"self": 0.9561824910080077,
"children": {
"process_trajectory": {
"total": 26.913620835993015,
"count": 44530,
"is_parallel": true,
"self": 25.24860966699316,
"children": {
"RLTrainer._checkpoint": {
"total": 1.665011168999854,
"count": 4,
"is_parallel": true,
"self": 1.665011168999854
}
}
},
"_update_policy": {
"total": 20.548386356000037,
"count": 9,
"is_parallel": true,
"self": 8.760645934000763,
"children": {
"TorchPPOOptimizer.update": {
"total": 11.787740421999274,
"count": 456,
"is_parallel": true,
"self": 11.787740421999274
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13510947499992199,
"count": 1,
"self": 0.0008442799999102135,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13426519500001177,
"count": 1,
"self": 0.13426519500001177
}
}
}
}
}
}
}