WillLedd's picture
First Push
7568038 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.8065742254257202,
"min": 1.8065742254257202,
"max": 2.8749797344207764,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 17964.57421875,
"min": 17964.57421875,
"max": 29853.7890625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 6.565771102905273,
"min": 0.10038803517818451,
"max": 6.565771102905273,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1667.705810546875,
"min": 24.494680404663086,
"max": 1667.705810546875,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 18.6,
"min": 2.909090909090909,
"max": 18.6,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1023.0,
"min": 128.0,
"max": 1023.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 18.6,
"min": 2.909090909090909,
"max": 18.6,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1023.0,
"min": 128.0,
"max": 1023.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07013711356058575,
"min": 0.06361517966303117,
"max": 0.07317403416263736,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.1402742271211715,
"min": 0.1281653938410207,
"max": 0.2147349014351711,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.24196990316405015,
"min": 0.08260086507260339,
"max": 0.24857052566568835,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.4839398063281003,
"min": 0.16520173014520678,
"max": 0.745711576997065,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.7440094512e-05,
"min": 2.7440094512e-05,
"max": 0.0004674400065119999,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.4880189024e-05,
"min": 5.4880189024e-05,
"max": 0.0009733201053359995,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10548799999999997,
"min": 0.10548799999999997,
"max": 0.19348800000000005,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.21097599999999994,
"min": 0.21097599999999994,
"max": 0.4946640000000001,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0046750512,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005677024,
"min": 0.0005677024,
"max": 0.009743733600000004,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1758028846",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758029062"
},
"total": 215.89770195100027,
"count": 1,
"self": 0.4420154600006754,
"children": {
"run_training.setup": {
"total": 0.02608651899981851,
"count": 1,
"self": 0.02608651899981851
},
"TrainerController.start_learning": {
"total": 215.42959997199978,
"count": 1,
"self": 0.19033804903574492,
"children": {
"TrainerController._reset_env": {
"total": 1.8791048129996852,
"count": 1,
"self": 1.8791048129996852
},
"TrainerController.advance": {
"total": 213.2816041369647,
"count": 9096,
"self": 0.1894361939675946,
"children": {
"env_step": {
"total": 153.1164440790103,
"count": 9096,
"self": 118.24083772101676,
"children": {
"SubprocessEnvManager._take_step": {
"total": 34.7627319139865,
"count": 9096,
"self": 0.6398590719791173,
"children": {
"TorchPolicy.evaluate": {
"total": 34.12287284200738,
"count": 9096,
"self": 34.12287284200738
}
}
},
"workers": {
"total": 0.11287444400704771,
"count": 9096,
"self": 0.0,
"children": {
"worker_root": {
"total": 214.6719944050251,
"count": 9096,
"is_parallel": true,
"self": 110.94648580003604,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002117198999712855,
"count": 1,
"is_parallel": true,
"self": 0.0006683979995614209,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001448801000151434,
"count": 10,
"is_parallel": true,
"self": 0.001448801000151434
}
}
},
"UnityEnvironment.step": {
"total": 0.04956701199989766,
"count": 1,
"is_parallel": true,
"self": 0.0006382470000971807,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000458063000223774,
"count": 1,
"is_parallel": true,
"self": 0.000458063000223774
},
"communicator.exchange": {
"total": 0.04638052299969786,
"count": 1,
"is_parallel": true,
"self": 0.04638052299969786
},
"steps_from_proto": {
"total": 0.0020901789998788445,
"count": 1,
"is_parallel": true,
"self": 0.00040099299940266064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016891860004761838,
"count": 10,
"is_parallel": true,
"self": 0.0016891860004761838
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 103.72550860498905,
"count": 9095,
"is_parallel": true,
"self": 4.85540816498451,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.7620857959918794,
"count": 9095,
"is_parallel": true,
"self": 2.7620857959918794
},
"communicator.exchange": {
"total": 80.20816184599789,
"count": 9095,
"is_parallel": true,
"self": 80.20816184599789
},
"steps_from_proto": {
"total": 15.899852798014763,
"count": 9095,
"is_parallel": true,
"self": 2.834395852061789,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.065456945952974,
"count": 90950,
"is_parallel": true,
"self": 13.065456945952974
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 59.97572386398679,
"count": 9096,
"self": 0.22491903098989496,
"children": {
"process_trajectory": {
"total": 14.670332511997458,
"count": 9096,
"self": 14.475773052997283,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19455945900017468,
"count": 2,
"self": 0.19455945900017468
}
}
},
"_update_policy": {
"total": 45.080472320999434,
"count": 22,
"self": 19.271350921002067,
"children": {
"TorchPPOOptimizer.update": {
"total": 25.809121399997366,
"count": 2241,
"self": 25.809121399997366
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.63999809755478e-07,
"count": 1,
"self": 9.63999809755478e-07
},
"TrainerController._save_models": {
"total": 0.07855200899984993,
"count": 1,
"self": 0.0008663670000714774,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07768564199977845,
"count": 1,
"self": 0.07768564199977845
}
}
}
}
}
}
}