wirthy21's picture
First Push
b473602 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0079158544540405,
"min": 1.0079158544540405,
"max": 2.868910789489746,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9656.841796875,
"min": 9656.841796875,
"max": 29443.630859375,
"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": 13.202203750610352,
"min": 0.33174172043800354,
"max": 13.202203750610352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2574.4296875,
"min": 64.35789489746094,
"max": 2663.74853515625,
"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": 0.06695117883211031,
"min": 0.06014262287056887,
"max": 0.07727193652136324,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26780471532844125,
"min": 0.24057049148227547,
"max": 0.38635968260681625,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19328540074182493,
"min": 0.10929865951595061,
"max": 0.2796934826116936,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7731416029672997,
"min": 0.43719463806380243,
"max": 1.398467413058468,
"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": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.477272727272727,
"min": 3.272727272727273,
"max": 26.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1165.0,
"min": 144.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.477272727272727,
"min": 3.272727272727273,
"max": 26.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1165.0,
"min": 144.0,
"max": 1415.0,
"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": "1733774419",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733774992"
},
"total": 573.0132293170001,
"count": 1,
"self": 0.4949170659999709,
"children": {
"run_training.setup": {
"total": 0.07897774299999583,
"count": 1,
"self": 0.07897774299999583
},
"TrainerController.start_learning": {
"total": 572.4393345080001,
"count": 1,
"self": 0.8619480929968404,
"children": {
"TrainerController._reset_env": {
"total": 6.177714108000032,
"count": 1,
"self": 6.177714108000032
},
"TrainerController.advance": {
"total": 565.3176881460032,
"count": 18205,
"self": 0.4149708439999813,
"children": {
"env_step": {
"total": 564.9027173020032,
"count": 18205,
"self": 432.849268051997,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.65187496601618,
"count": 18205,
"self": 2.0265453089975836,
"children": {
"TorchPolicy.evaluate": {
"total": 129.6253296570186,
"count": 18205,
"self": 129.6253296570186
}
}
},
"workers": {
"total": 0.401574283990044,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 570.7055802139886,
"count": 18205,
"is_parallel": true,
"self": 273.910104107983,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0034054750000223066,
"count": 1,
"is_parallel": true,
"self": 0.0010780680000834764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023274069999388303,
"count": 10,
"is_parallel": true,
"self": 0.0023274069999388303
}
}
},
"UnityEnvironment.step": {
"total": 0.08452658499993504,
"count": 1,
"is_parallel": true,
"self": 0.0011008870000068782,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047366799992687447,
"count": 1,
"is_parallel": true,
"self": 0.00047366799992687447
},
"communicator.exchange": {
"total": 0.07685853499992845,
"count": 1,
"is_parallel": true,
"self": 0.07685853499992845
},
"steps_from_proto": {
"total": 0.006093495000072835,
"count": 1,
"is_parallel": true,
"self": 0.003961409000112326,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002132085999960509,
"count": 10,
"is_parallel": true,
"self": 0.002132085999960509
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 296.7954761060056,
"count": 18204,
"is_parallel": true,
"self": 13.538229646007608,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.964423214990461,
"count": 18204,
"is_parallel": true,
"self": 6.964423214990461
},
"communicator.exchange": {
"total": 233.3962486340032,
"count": 18204,
"is_parallel": true,
"self": 233.3962486340032
},
"steps_from_proto": {
"total": 42.896574611004326,
"count": 18204,
"is_parallel": true,
"self": 8.416855184978886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.47971942602544,
"count": 182040,
"is_parallel": true,
"self": 34.47971942602544
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016182500007744238,
"count": 1,
"self": 0.00016182500007744238,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 558.4939100710029,
"count": 749751,
"is_parallel": true,
"self": 17.6928238900216,
"children": {
"process_trajectory": {
"total": 299.30663326898195,
"count": 749751,
"is_parallel": true,
"self": 298.5958035319819,
"children": {
"RLTrainer._checkpoint": {
"total": 0.71082973700004,
"count": 4,
"is_parallel": true,
"self": 0.71082973700004
}
}
},
"_update_policy": {
"total": 241.49445291199936,
"count": 90,
"is_parallel": true,
"self": 67.39526914399801,
"children": {
"TorchPPOOptimizer.update": {
"total": 174.09918376800135,
"count": 4587,
"is_parallel": true,
"self": 174.09918376800135
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08182233599995925,
"count": 1,
"self": 0.0011003429999618675,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08072199299999738,
"count": 1,
"self": 0.08072199299999738
}
}
}
}
}
}
}