vinben007's picture
First Push
11b38a3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6836230158805847,
"min": 0.6836230158805847,
"max": 2.868382453918457,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7459.6943359375,
"min": 6249.99609375,
"max": 31331.341796875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.843011856079102,
"min": 0.38432446122169495,
"max": 14.03917121887207,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1398.1441650390625,
"min": 37.27947235107422,
"max": 1444.0274658203125,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 6766.0,
"max": 13134.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.22641509433962,
"min": 3.4545454545454546,
"max": 27.62962962962963,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1443.0,
"min": 152.0,
"max": 1501.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.22641509433962,
"min": 3.4545454545454546,
"max": 27.62962962962963,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1443.0,
"min": 152.0,
"max": 1501.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06952805537860948,
"min": 0.061416285412814145,
"max": 0.07584178660397821,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3476402768930474,
"min": 0.24566514165125658,
"max": 0.37920893301989106,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17888556830645874,
"min": 0.13488786752773996,
"max": 0.29660745942873845,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8944278415322937,
"min": 0.5395514701109598,
"max": 1.4672198798495277,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0346589884799973e-06,
"min": 3.0346589884799973e-06,
"max": 0.0002967432010856,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5173294942399986e-05,
"min": 1.5173294942399986e-05,
"max": 0.0014538000153999995,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101152,
"min": 0.10101152,
"max": 0.19891440000000002,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050576,
"min": 0.4119487999999999,
"max": 0.9846000000000001,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.047484799999996e-05,
"min": 6.047484799999996e-05,
"max": 0.004945828560000001,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003023742399999998,
"min": 0.0003023742399999998,
"max": 0.02423154,
"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": "1696977518",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1696978895"
},
"total": 1376.906688365,
"count": 1,
"self": 0.4314744289999908,
"children": {
"run_training.setup": {
"total": 0.04536520900001051,
"count": 1,
"self": 0.04536520900001051
},
"TrainerController.start_learning": {
"total": 1376.429848727,
"count": 1,
"self": 1.861188756981619,
"children": {
"TrainerController._reset_env": {
"total": 8.786656794999999,
"count": 1,
"self": 8.786656794999999
},
"TrainerController.advance": {
"total": 1365.6864265880185,
"count": 45601,
"self": 0.853174140017245,
"children": {
"env_step": {
"total": 1364.8332524480013,
"count": 45601,
"self": 841.2795964300061,
"children": {
"SubprocessEnvManager._take_step": {
"total": 522.6975269309906,
"count": 45601,
"self": 4.419066021985145,
"children": {
"TorchPolicy.evaluate": {
"total": 518.2784609090055,
"count": 45601,
"self": 518.2784609090055
}
}
},
"workers": {
"total": 0.8561290870045468,
"count": 45601,
"self": 0.0,
"children": {
"worker_root": {
"total": 1372.3270516659818,
"count": 45601,
"is_parallel": true,
"self": 688.1332918989924,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030222980000189636,
"count": 1,
"is_parallel": true,
"self": 0.0007966999999098334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022255980001091302,
"count": 10,
"is_parallel": true,
"self": 0.0022255980001091302
}
}
},
"UnityEnvironment.step": {
"total": 0.04367598800001815,
"count": 1,
"is_parallel": true,
"self": 0.0006563770001548619,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004737519999480355,
"count": 1,
"is_parallel": true,
"self": 0.0004737519999480355
},
"communicator.exchange": {
"total": 0.040335765000008905,
"count": 1,
"is_parallel": true,
"self": 0.040335765000008905
},
"steps_from_proto": {
"total": 0.0022100939999063485,
"count": 1,
"is_parallel": true,
"self": 0.000415318000023035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017947759998833135,
"count": 10,
"is_parallel": true,
"self": 0.0017947759998833135
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 684.1937597669894,
"count": 45600,
"is_parallel": true,
"self": 28.297928885982515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.913427982998314,
"count": 45600,
"is_parallel": true,
"self": 14.913427982998314
},
"communicator.exchange": {
"total": 537.7439824649894,
"count": 45600,
"is_parallel": true,
"self": 537.7439824649894
},
"steps_from_proto": {
"total": 103.2384204330192,
"count": 45600,
"is_parallel": true,
"self": 20.048184875059405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.1902355579598,
"count": 456000,
"is_parallel": true,
"self": 83.1902355579598
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000968792999856305,
"count": 1,
"self": 0.000968792999856305,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1365.9250596570257,
"count": 179090,
"is_parallel": true,
"self": 3.922600768084749,
"children": {
"process_trajectory": {
"total": 208.10092181194125,
"count": 179090,
"is_parallel": true,
"self": 206.04752270694144,
"children": {
"RLTrainer._checkpoint": {
"total": 2.053399104999812,
"count": 10,
"is_parallel": true,
"self": 2.053399104999812
}
}
},
"_update_policy": {
"total": 1153.9015370769996,
"count": 227,
"is_parallel": true,
"self": 375.1595169290074,
"children": {
"TorchPPOOptimizer.update": {
"total": 778.7420201479922,
"count": 19295,
"is_parallel": true,
"self": 778.7420201479922
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09460779400001229,
"count": 1,
"self": 0.000981374000048163,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09362641999996413,
"count": 1,
"self": 0.09362641999996413
}
}
}
}
}
}
}