Alopezcordero's picture
First training of SnowballTarget
71b68c0 verified
Raw
History Blame Contribute Delete
18.6 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.3290817737579346,
"min": 2.3290817737579346,
"max": 2.8902676105499268,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 22340.552734375,
"min": 22340.552734375,
"max": 29631.0234375,
"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": 4.242885589599609,
"min": -0.0761304646730423,
"max": 4.242885589599609,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 827.3626708984375,
"min": -14.769309997558594,
"max": 839.4366455078125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 10.522727272727273,
"min": 2.909090909090909,
"max": 10.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 463.0,
"min": 128.0,
"max": 557.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 10.522727272727273,
"min": 2.909090909090909,
"max": 10.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 463.0,
"min": 128.0,
"max": 557.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.015098982110309104,
"min": 0.010033971800779303,
"max": 0.02169582078543802,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.015098982110309104,
"min": 0.010033971800779303,
"max": 0.02169582078543802,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3166947265466054,
"min": 0.11482972304026286,
"max": 0.33993866443634035,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3166947265466054,
"min": 0.11482972304026286,
"max": 0.33993866443634035,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.132098956000001e-06,
"min": 3.132098956000001e-06,
"max": 0.0002842080052639999,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.132098956000001e-06,
"min": 3.132098956000001e-06,
"max": 0.0002842080052639999,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10104399999999997,
"min": 0.10104399999999997,
"max": 0.19473599999999996,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10104399999999997,
"min": 0.10104399999999997,
"max": 0.19473599999999996,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.209560000000005e-05,
"min": 6.209560000000005e-05,
"max": 0.0047373264,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 6.209560000000005e-05,
"min": 6.209560000000005e-05,
"max": 0.0047373264,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1780648886",
"python_version": "3.8.20 (default, Oct 3 2024, 15:24:27) \n[GCC 11.2.0]",
"command_line_arguments": "/home/alejandrolopezcordero01/miniconda3/envs/snowball-rl/bin/mlagents-learn ./ppo-huggyDog/ml-agents/config/ppo/SnowballTarget.yaml --env=./snowball-env/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --train --no-graphics --force --torch-device cpu",
"mlagents_version": "0.30.0",
"mlagents_envs_version": "0.30.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1780649201"
},
"total": 314.1203029304743,
"count": 1,
"self": 0.2706284373998642,
"children": {
"run_training.setup": {
"total": 0.011774390935897827,
"count": 1,
"self": 0.011774390935897827
},
"TrainerController.start_learning": {
"total": 313.8379001021385,
"count": 1,
"self": 0.33062250912189484,
"children": {
"TrainerController._reset_env": {
"total": 0.6792698353528976,
"count": 1,
"self": 0.6792698353528976
},
"TrainerController.advance": {
"total": 312.65391694009304,
"count": 18218,
"self": 0.16272152960300446,
"children": {
"env_step": {
"total": 312.49119541049004,
"count": 18218,
"self": 266.8444172143936,
"children": {
"SubprocessEnvManager._take_step": {
"total": 45.45669834315777,
"count": 18218,
"self": 1.1533027738332748,
"children": {
"TorchPolicy.evaluate": {
"total": 44.30339556932449,
"count": 18218,
"self": 44.30339556932449
}
}
},
"workers": {
"total": 0.19007985293865204,
"count": 18218,
"self": 0.0,
"children": {
"worker_root": {
"total": 313.2689013928175,
"count": 18218,
"is_parallel": true,
"self": 164.52592119574547,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001460149884223938,
"count": 1,
"is_parallel": true,
"self": 0.0004010051488876343,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010591447353363037,
"count": 10,
"is_parallel": true,
"self": 0.0010591447353363037
}
}
},
"UnityEnvironment.step": {
"total": 0.0374051034450531,
"count": 1,
"is_parallel": true,
"self": 0.0003062933683395386,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021412968635559082,
"count": 1,
"is_parallel": true,
"self": 0.00021412968635559082
},
"communicator.exchange": {
"total": 0.035905495285987854,
"count": 1,
"is_parallel": true,
"self": 0.035905495285987854
},
"steps_from_proto": {
"total": 0.0009791851043701172,
"count": 1,
"is_parallel": true,
"self": 0.00020493566989898682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007742494344711304,
"count": 10,
"is_parallel": true,
"self": 0.0007742494344711304
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 148.74298019707203,
"count": 18217,
"is_parallel": true,
"self": 5.109900459647179,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.918840706348419,
"count": 18217,
"is_parallel": true,
"self": 2.918840706348419
},
"communicator.exchange": {
"total": 125.43075959384441,
"count": 18217,
"is_parallel": true,
"self": 125.43075959384441
},
"steps_from_proto": {
"total": 15.283479437232018,
"count": 18217,
"is_parallel": true,
"self": 3.1103400737047195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 12.173139363527298,
"count": 182170,
"is_parallel": true,
"self": 12.173139363527298
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002046525478363037,
"count": 1,
"self": 0.0002046525478363037,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 311.47200487554073,
"count": 326297,
"is_parallel": true,
"self": 3.453059360384941,
"children": {
"process_trajectory": {
"total": 189.645842730999,
"count": 326297,
"is_parallel": true,
"self": 188.37623898684978,
"children": {
"RLTrainer._checkpoint": {
"total": 1.269603744149208,
"count": 4,
"is_parallel": true,
"self": 1.269603744149208
}
}
},
"_update_policy": {
"total": 118.3731027841568,
"count": 19,
"is_parallel": true,
"self": 50.42044943571091,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.95265334844589,
"count": 285,
"is_parallel": true,
"self": 67.95265334844589
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17388616502285004,
"count": 1,
"self": 0.008532389998435974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16535377502441406,
"count": 1,
"self": 0.16535377502441406
}
}
}
}
}
}
}