snj144's picture
First training of SnowballTarget
09ad95d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0845375061035156,
"min": 1.0845375061035156,
"max": 2.8663222789764404,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10367.09375,
"min": 10367.09375,
"max": 29385.53515625,
"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": 12.396291732788086,
"min": 0.24953381717205048,
"max": 12.396291732788086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2417.27685546875,
"min": 48.40956115722656,
"max": 2492.5400390625,
"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": 0.06723442294106444,
"min": 0.06255615251846429,
"max": 0.07633128786512637,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26893769176425775,
"min": 0.25022461007385716,
"max": 0.3774870893046004,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19553694245862024,
"min": 0.09269415568583189,
"max": 0.2832083855189529,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.782147769834481,
"min": 0.37077662274332757,
"max": 1.4160419275947644,
"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": 24.795454545454547,
"min": 2.6136363636363638,
"max": 24.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1091.0,
"min": 115.0,
"max": 1340.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.795454545454547,
"min": 2.6136363636363638,
"max": 24.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1091.0,
"min": 115.0,
"max": 1340.0,
"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": "1730207917",
"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=SnowballTarget --resume --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730208513"
},
"total": 595.781671991,
"count": 1,
"self": 0.6373178569999709,
"children": {
"run_training.setup": {
"total": 0.06633670700000494,
"count": 1,
"self": 0.06633670700000494
},
"TrainerController.start_learning": {
"total": 595.0780174270001,
"count": 1,
"self": 0.8588921320064173,
"children": {
"TrainerController._reset_env": {
"total": 2.2574645259999784,
"count": 1,
"self": 2.2574645259999784
},
"TrainerController.advance": {
"total": 591.8750005069937,
"count": 18202,
"self": 0.40297420499757663,
"children": {
"env_step": {
"total": 591.4720263019962,
"count": 18202,
"self": 454.85142795298515,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.20202199701282,
"count": 18202,
"self": 2.1949359380036526,
"children": {
"TorchPolicy.evaluate": {
"total": 134.00708605900917,
"count": 18202,
"self": 134.00708605900917
}
}
},
"workers": {
"total": 0.4185763519981833,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 593.3004639519987,
"count": 18202,
"is_parallel": true,
"self": 285.0453167930126,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024240500000018983,
"count": 1,
"is_parallel": true,
"self": 0.0007028179999792883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00172123200002261,
"count": 10,
"is_parallel": true,
"self": 0.00172123200002261
}
}
},
"UnityEnvironment.step": {
"total": 0.04396443799998906,
"count": 1,
"is_parallel": true,
"self": 0.0007884300000569056,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005499829999848771,
"count": 1,
"is_parallel": true,
"self": 0.0005499829999848771
},
"communicator.exchange": {
"total": 0.04027167599997483,
"count": 1,
"is_parallel": true,
"self": 0.04027167599997483
},
"steps_from_proto": {
"total": 0.0023543489999724443,
"count": 1,
"is_parallel": true,
"self": 0.0004418070000724583,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001912541999899986,
"count": 10,
"is_parallel": true,
"self": 0.001912541999899986
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 308.2551471589861,
"count": 18201,
"is_parallel": true,
"self": 14.330440385977568,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.224129895998715,
"count": 18201,
"is_parallel": true,
"self": 7.224129895998715
},
"communicator.exchange": {
"total": 243.90383070399935,
"count": 18201,
"is_parallel": true,
"self": 243.90383070399935
},
"steps_from_proto": {
"total": 42.79674617301049,
"count": 18201,
"is_parallel": true,
"self": 8.32786874899864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.46887742401185,
"count": 182010,
"is_parallel": true,
"self": 34.46887742401185
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0005899029999909544,
"count": 1,
"self": 0.0005899029999909544,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 585.182266394957,
"count": 771525,
"is_parallel": true,
"self": 17.252427710983852,
"children": {
"process_trajectory": {
"total": 307.5071588109731,
"count": 771525,
"is_parallel": true,
"self": 306.84791214997324,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6592466609998837,
"count": 4,
"is_parallel": true,
"self": 0.6592466609998837
}
}
},
"_update_policy": {
"total": 260.422679873,
"count": 90,
"is_parallel": true,
"self": 75.24008867000293,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.18259120299706,
"count": 4587,
"is_parallel": true,
"self": 185.18259120299706
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08607035900001847,
"count": 1,
"self": 0.0013810250000005908,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08468933400001788,
"count": 1,
"self": 0.08468933400001788
}
}
}
}
}
}
}