sarahpuspdew's picture
First Push
f843845
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7682623863220215,
"min": 0.7447479367256165,
"max": 2.870447874069214,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7462.1328125,
"min": 7099.0712890625,
"max": 29396.2578125,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.716470718383789,
"min": 0.21843239665031433,
"max": 13.756585121154785,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2811.87646484375,
"min": 42.375885009765625,
"max": 2820.099853515625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07175667212303619,
"min": 0.059202948685589375,
"max": 0.07568241104759806,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3587833606151809,
"min": 0.2368117947423575,
"max": 0.37841205523799026,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19884419336038478,
"min": 0.13139768971778526,
"max": 0.2849476350580945,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9942209668019238,
"min": 0.525590758871141,
"max": 1.4047678571705726,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.6,
"min": 3.5454545454545454,
"max": 27.666666666666668,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1463.0,
"min": 156.0,
"max": 1483.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.6,
"min": 3.5454545454545454,
"max": 27.666666666666668,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1463.0,
"min": 156.0,
"max": 1483.0,
"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": "1685089234",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1685090392"
},
"total": 1158.6396205519998,
"count": 1,
"self": 0.5256784389998757,
"children": {
"run_training.setup": {
"total": 0.036989618000006885,
"count": 1,
"self": 0.036989618000006885
},
"TrainerController.start_learning": {
"total": 1158.076952495,
"count": 1,
"self": 1.4082330509720578,
"children": {
"TrainerController._reset_env": {
"total": 3.4439129380000395,
"count": 1,
"self": 3.4439129380000395
},
"TrainerController.advance": {
"total": 1153.0075769520274,
"count": 45497,
"self": 0.6417343620639713,
"children": {
"env_step": {
"total": 1152.3658425899634,
"count": 45497,
"self": 845.5346355269776,
"children": {
"SubprocessEnvManager._take_step": {
"total": 306.1853417520158,
"count": 45497,
"self": 4.305286445048296,
"children": {
"TorchPolicy.evaluate": {
"total": 301.8800553069675,
"count": 45497,
"self": 301.8800553069675
}
}
},
"workers": {
"total": 0.6458653109700663,
"count": 45497,
"self": 0.0,
"children": {
"worker_root": {
"total": 1153.954513292001,
"count": 45497,
"is_parallel": true,
"self": 538.4148632490319,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021137429998816515,
"count": 1,
"is_parallel": true,
"self": 0.000637758999801008,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014759840000806435,
"count": 10,
"is_parallel": true,
"self": 0.0014759840000806435
}
}
},
"UnityEnvironment.step": {
"total": 0.035471856999947704,
"count": 1,
"is_parallel": true,
"self": 0.0005694490000678343,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003209779999906459,
"count": 1,
"is_parallel": true,
"self": 0.0003209779999906459
},
"communicator.exchange": {
"total": 0.03237414899990654,
"count": 1,
"is_parallel": true,
"self": 0.03237414899990654
},
"steps_from_proto": {
"total": 0.002207280999982686,
"count": 1,
"is_parallel": true,
"self": 0.0004268590000719996,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017804219999106863,
"count": 10,
"is_parallel": true,
"self": 0.0017804219999106863
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 615.539650042969,
"count": 45496,
"is_parallel": true,
"self": 23.9180753230155,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.460605158969656,
"count": 45496,
"is_parallel": true,
"self": 13.460605158969656
},
"communicator.exchange": {
"total": 492.85593980498766,
"count": 45496,
"is_parallel": true,
"self": 492.85593980498766
},
"steps_from_proto": {
"total": 85.3050297559962,
"count": 45496,
"is_parallel": true,
"self": 16.488985102958623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.81604465303758,
"count": 454960,
"is_parallel": true,
"self": 68.81604465303758
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018459400007486693,
"count": 1,
"self": 0.00018459400007486693,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1144.4248634901141,
"count": 1073151,
"is_parallel": true,
"self": 23.702225430271028,
"children": {
"process_trajectory": {
"total": 624.0049290918416,
"count": 1073151,
"is_parallel": true,
"self": 621.3787924838416,
"children": {
"RLTrainer._checkpoint": {
"total": 2.6261366080000244,
"count": 10,
"is_parallel": true,
"self": 2.6261366080000244
}
}
},
"_update_policy": {
"total": 496.7177089680015,
"count": 227,
"is_parallel": true,
"self": 192.26401737397896,
"children": {
"TorchPPOOptimizer.update": {
"total": 304.45369159402253,
"count": 11574,
"is_parallel": true,
"self": 304.45369159402253
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21704496000029394,
"count": 1,
"self": 0.0018278290003763686,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21521713099991757,
"count": 1,
"self": 0.21521713099991757
}
}
}
}
}
}
}