q-SnowballTarget / run_logs /timers.json
MysteryManav's picture
SnowballTarget
e20ec12 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7713654041290283,
"min": 0.7058430314064026,
"max": 2.7871124744415283,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 15273.03515625,
"min": 13975.6923828125,
"max": 57146.953125,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 19992.0,
"max": 999952.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 19992.0,
"max": 999952.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.311433792114258,
"min": 0.9383178353309631,
"max": 14.37216567993164,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 5710.26220703125,
"min": 374.3888244628906,
"max": 5781.15771484375,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06689777244062493,
"min": 0.06322509537698322,
"max": 0.07288012154531474,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.6020799519656244,
"min": 0.5690258583928489,
"max": 0.6990882444612604,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1538192628840216,
"min": 0.1443460942093843,
"max": 0.28104940910614656,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.3843733659561943,
"min": 1.2991148478844587,
"max": 2.529444681955319,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0264989911999997e-06,
"min": 3.0264989911999997e-06,
"max": 0.00029672640109119994,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.72384909208e-05,
"min": 2.72384909208e-05,
"max": 0.0026705376098207995,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10100880000000001,
"min": 0.10100880000000001,
"max": 0.1989088,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.9090792000000001,
"min": 0.9090792000000001,
"max": 1.7901791999999999,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0339119999999994e-05,
"min": 6.0339119999999994e-05,
"max": 0.00494554912,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005430520799999999,
"min": 0.0005430520799999999,
"max": 0.04450994208,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 19701.0,
"min": 19701.0,
"max": 21890.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.303030303030305,
"min": 5.757575757575758,
"max": 28.303030303030305,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 2802.0,
"min": 570.0,
"max": 3037.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.303030303030305,
"min": 5.757575757575758,
"max": 28.303030303030305,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 2802.0,
"min": 570.0,
"max": 3037.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1748872476",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/manav/Code/AIML/DRL/.conda/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --width=1280 --height=720 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748873827"
},
"total": 1350.9069259240005,
"count": 1,
"self": 1.0637655530008487,
"children": {
"run_training.setup": {
"total": 0.020917910000207485,
"count": 1,
"self": 0.020917910000207485
},
"TrainerController.start_learning": {
"total": 1349.8222424609994,
"count": 1,
"self": 1.590281933940787,
"children": {
"TrainerController._reset_env": {
"total": 1.786696381001093,
"count": 1,
"self": 1.786696381001093
},
"TrainerController.advance": {
"total": 1346.2494775780578,
"count": 90928,
"self": 1.5996849833336455,
"children": {
"env_step": {
"total": 929.4366662100292,
"count": 90928,
"self": 680.8426842890258,
"children": {
"SubprocessEnvManager._take_step": {
"total": 247.53564174976054,
"count": 90928,
"self": 4.768349892021433,
"children": {
"TorchPolicy.evaluate": {
"total": 242.7672918577391,
"count": 90928,
"self": 242.7672918577391
}
}
},
"workers": {
"total": 1.0583401712428895,
"count": 90928,
"self": 0.0,
"children": {
"worker_root": {
"total": 1347.3265317070145,
"count": 90928,
"is_parallel": true,
"self": 772.7373323594602,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014423630000237608,
"count": 1,
"is_parallel": true,
"self": 0.00040456200440530665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010378009956184542,
"count": 10,
"is_parallel": true,
"self": 0.0010378009956184542
}
}
},
"UnityEnvironment.step": {
"total": 0.022094554999057436,
"count": 1,
"is_parallel": true,
"self": 0.00025103399821091443,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021005199960200116,
"count": 1,
"is_parallel": true,
"self": 0.00021005199960200116
},
"communicator.exchange": {
"total": 0.0206373609998991,
"count": 1,
"is_parallel": true,
"self": 0.0206373609998991
},
"steps_from_proto": {
"total": 0.0009961080013454193,
"count": 1,
"is_parallel": true,
"self": 0.00017358199693262577,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008225260044127936,
"count": 10,
"is_parallel": true,
"self": 0.0008225260044127936
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 574.5891993475543,
"count": 90927,
"is_parallel": true,
"self": 22.49901147006858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.9481893847842,
"count": 90927,
"is_parallel": true,
"self": 12.9481893847842
},
"communicator.exchange": {
"total": 472.0681196437363,
"count": 90927,
"is_parallel": true,
"self": 472.0681196437363
},
"steps_from_proto": {
"total": 67.07387884896525,
"count": 90927,
"is_parallel": true,
"self": 14.65100613965842,
"children": {
"_process_rank_one_or_two_observation": {
"total": 52.42287270930683,
"count": 909270,
"is_parallel": true,
"self": 52.42287270930683
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 415.213126384695,
"count": 90928,
"self": 2.03284699379401,
"children": {
"process_trajectory": {
"total": 87.78375979090924,
"count": 90928,
"self": 85.65173599091031,
"children": {
"RLTrainer._checkpoint": {
"total": 2.132023799998933,
"count": 10,
"self": 2.132023799998933
}
}
},
"_update_policy": {
"total": 325.39651959999173,
"count": 454,
"self": 129.20730124482725,
"children": {
"TorchPPOOptimizer.update": {
"total": 196.18921835516448,
"count": 23151,
"self": 196.18921835516448
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.310001481324434e-07,
"count": 1,
"self": 6.310001481324434e-07
},
"TrainerController._save_models": {
"total": 0.19578593699952762,
"count": 1,
"self": 0.002276352999615483,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19350958399991214,
"count": 1,
"self": 0.19350958399991214
}
}
}
}
}
}
}