dhruvil122's picture
First Push
fc93c62 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9569052457809448,
"min": 0.9569052457809448,
"max": 2.8678629398345947,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9157.5830078125,
"min": 9157.5830078125,
"max": 29559.064453125,
"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": 12.975050926208496,
"min": 0.34695568680763245,
"max": 12.975050926208496,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2530.135009765625,
"min": 67.30940246582031,
"max": 2618.080078125,
"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": 0.0692386814804266,
"min": 0.059498984805638123,
"max": 0.08051024423840834,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2769547259217064,
"min": 0.2379959392225525,
"max": 0.36299386560716024,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20665681311020662,
"min": 0.10895563444515288,
"max": 0.2975606713809219,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8266272524408265,
"min": 0.43582253778061153,
"max": 1.4391096427342762,
"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": 25.636363636363637,
"min": 2.909090909090909,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 128.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 2.909090909090909,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 128.0,
"max": 1405.0,
"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": "1733778427",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force",
"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": "1733779051"
},
"total": 623.629514383,
"count": 1,
"self": 1.1550191999999697,
"children": {
"run_training.setup": {
"total": 0.07348898800000825,
"count": 1,
"self": 0.07348898800000825
},
"TrainerController.start_learning": {
"total": 622.401006195,
"count": 1,
"self": 0.8896224299957112,
"children": {
"TrainerController._reset_env": {
"total": 6.876591256999973,
"count": 1,
"self": 6.876591256999973
},
"TrainerController.advance": {
"total": 614.500853058004,
"count": 18207,
"self": 0.4282876480060622,
"children": {
"env_step": {
"total": 614.072565409998,
"count": 18207,
"self": 473.58706900800826,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.06491335700093,
"count": 18207,
"self": 2.52739675400818,
"children": {
"TorchPolicy.evaluate": {
"total": 137.53751660299275,
"count": 18207,
"self": 137.53751660299275
}
}
},
"workers": {
"total": 0.4205830449888026,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 620.345840813005,
"count": 18207,
"is_parallel": true,
"self": 295.977453455999,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0028782869999872673,
"count": 1,
"is_parallel": true,
"self": 0.0010079249998966588,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018703620000906085,
"count": 10,
"is_parallel": true,
"self": 0.0018703620000906085
}
}
},
"UnityEnvironment.step": {
"total": 0.09679205599996976,
"count": 1,
"is_parallel": true,
"self": 0.0008589529999767365,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004758069999866166,
"count": 1,
"is_parallel": true,
"self": 0.0004758069999866166
},
"communicator.exchange": {
"total": 0.09260499800001298,
"count": 1,
"is_parallel": true,
"self": 0.09260499800001298
},
"steps_from_proto": {
"total": 0.002852297999993425,
"count": 1,
"is_parallel": true,
"self": 0.0004737149999414214,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023785830000520036,
"count": 10,
"is_parallel": true,
"self": 0.0023785830000520036
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 324.368387357006,
"count": 18206,
"is_parallel": true,
"self": 15.069157900027506,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.616237197992177,
"count": 18206,
"is_parallel": true,
"self": 7.616237197992177
},
"communicator.exchange": {
"total": 256.2205534639951,
"count": 18206,
"is_parallel": true,
"self": 256.2205534639951
},
"steps_from_proto": {
"total": 45.462438794991215,
"count": 18206,
"is_parallel": true,
"self": 8.849001263991681,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.61343753099953,
"count": 182060,
"is_parallel": true,
"self": 36.61343753099953
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021054300009382132,
"count": 1,
"self": 0.00021054300009382132,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 607.7624096860424,
"count": 723122,
"is_parallel": true,
"self": 17.669353016035757,
"children": {
"process_trajectory": {
"total": 328.328173909006,
"count": 723122,
"is_parallel": true,
"self": 327.16905037600617,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1591235329998426,
"count": 4,
"is_parallel": true,
"self": 1.1591235329998426
}
}
},
"_update_policy": {
"total": 261.7648827610006,
"count": 90,
"is_parallel": true,
"self": 72.27052335899708,
"children": {
"TorchPPOOptimizer.update": {
"total": 189.4943594020035,
"count": 4584,
"is_parallel": true,
"self": 189.4943594020035
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13372890700020434,
"count": 1,
"self": 0.004035164000015357,
"children": {
"RLTrainer._checkpoint": {
"total": 0.129693743000189,
"count": 1,
"self": 0.129693743000189
}
}
}
}
}
}
}