Peter Mai
First Push
dc87275 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.7325496673583984,
"min": 2.7325496673583984,
"max": 2.859252691268921,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 28104.2734375,
"min": 28104.2734375,
"max": 29313.05859375,
"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": 1.30037260055542,
"min": 0.3008142411708832,
"max": 1.30037260055542,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 266.5763854980469,
"min": 58.35796356201172,
"max": 266.5763854980469,
"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": 0.06838757983322127,
"min": 0.06838757983322127,
"max": 0.07409834564864201,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34193789916610634,
"min": 0.29639338259456804,
"max": 0.34193789916610634,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20119986428933984,
"min": 0.11386092805746467,
"max": 0.20119986428933984,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0059993214466991,
"min": 0.4554437122298587,
"max": 1.0059993214466991,
"count": 2
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.000277032007656,
"min": 0.000277032007656,
"max": 0.000291882002706,
"count": 2
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00138516003828,
"min": 0.001167528010824,
"max": 0.00138516003828,
"count": 2
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.19234400000000001,
"min": 0.19234400000000001,
"max": 0.19729400000000002,
"count": 2
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.96172,
"min": 0.7891760000000001,
"max": 0.96172,
"count": 2
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0046179656,
"min": 0.0046179656,
"max": 0.0048649706,
"count": 2
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.023089828,
"min": 0.0194598824,
"max": 0.023089828,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 5.909090909090909,
"min": 3.4318181818181817,
"max": 5.909090909090909,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 325.0,
"min": 151.0,
"max": 325.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.909090909090909,
"min": 3.4318181818181817,
"max": 5.909090909090909,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 325.0,
"min": 151.0,
"max": 325.0,
"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": "1727308156",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727308256"
},
"total": 99.8609577279999,
"count": 1,
"self": 0.4710135539994553,
"children": {
"run_training.setup": {
"total": 0.0962654080003631,
"count": 1,
"self": 0.0962654080003631
},
"TrainerController.start_learning": {
"total": 99.29367876600008,
"count": 1,
"self": 0.1457150799988085,
"children": {
"TrainerController._reset_env": {
"total": 4.744749916999808,
"count": 1,
"self": 4.744749916999808
},
"TrainerController.advance": {
"total": 94.13488252400157,
"count": 2497,
"self": 0.06787056500934341,
"children": {
"env_step": {
"total": 94.06701195899223,
"count": 2497,
"self": 71.81203040398714,
"children": {
"SubprocessEnvManager._take_step": {
"total": 22.1858249389943,
"count": 2497,
"self": 0.4364564319889723,
"children": {
"TorchPolicy.evaluate": {
"total": 21.74936850700533,
"count": 2497,
"self": 21.74936850700533
}
}
},
"workers": {
"total": 0.06915661601078682,
"count": 2496,
"self": 0.0,
"children": {
"worker_root": {
"total": 98.74280472500504,
"count": 2496,
"is_parallel": true,
"self": 47.580354204029845,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.012732300000152463,
"count": 1,
"is_parallel": true,
"self": 0.006495634999737376,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006236665000415087,
"count": 10,
"is_parallel": true,
"self": 0.006236665000415087
}
}
},
"UnityEnvironment.step": {
"total": 0.14503138700001728,
"count": 1,
"is_parallel": true,
"self": 0.0011614580002969888,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005273929996292281,
"count": 1,
"is_parallel": true,
"self": 0.0005273929996292281
},
"communicator.exchange": {
"total": 0.13689386700025352,
"count": 1,
"is_parallel": true,
"self": 0.13689386700025352
},
"steps_from_proto": {
"total": 0.006448668999837537,
"count": 1,
"is_parallel": true,
"self": 0.0005818569998154999,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005866812000022037,
"count": 10,
"is_parallel": true,
"self": 0.005866812000022037
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 51.1624505209752,
"count": 2495,
"is_parallel": true,
"self": 2.5225209179793637,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.222818695011938,
"count": 2495,
"is_parallel": true,
"self": 1.222818695011938
},
"communicator.exchange": {
"total": 40.354416465987015,
"count": 2495,
"is_parallel": true,
"self": 40.354416465987015
},
"steps_from_proto": {
"total": 7.062694441996882,
"count": 2495,
"is_parallel": true,
"self": 1.4584396689879213,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.604254773008961,
"count": 24950,
"is_parallel": true,
"self": 5.604254773008961
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.177000017894898e-05,
"count": 1,
"self": 8.177000017894898e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 92.95161994497539,
"count": 136041,
"is_parallel": true,
"self": 3.091240392904183,
"children": {
"process_trajectory": {
"total": 53.51914273907096,
"count": 136041,
"is_parallel": true,
"self": 53.51914273907096
},
"_update_policy": {
"total": 36.34123681300025,
"count": 12,
"is_parallel": true,
"self": 9.764964134004458,
"children": {
"TorchPPOOptimizer.update": {
"total": 26.576272678995792,
"count": 609,
"is_parallel": true,
"self": 26.576272678995792
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2682494749997204,
"count": 1,
"self": 0.002020139999785897,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2662293349999345,
"count": 1,
"self": 0.2662293349999345
}
}
}
}
}
}
}