ZDPLI's picture
First Push
d7d2310
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9133097529411316,
"min": 0.9133097529411316,
"max": 2.8650121688842773,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8720.28125,
"min": 8720.28125,
"max": 29340.58984375,
"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": 12.99691390991211,
"min": 0.36053231358528137,
"max": 12.99691390991211,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.398193359375,
"min": 69.94326782226562,
"max": 2629.114990234375,
"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": 0.06004634319106117,
"min": 0.06004634319106117,
"max": 0.07651061248593488,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24018537276424468,
"min": 0.24018537276424468,
"max": 0.3741728264819055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18968126612404984,
"min": 0.12592493821912462,
"max": 0.2754903789244446,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7587250644961994,
"min": 0.5036997528764985,
"max": 1.377451894622223,
"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": 26.0,
"min": 3.25,
"max": 26.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1144.0,
"min": 143.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.0,
"min": 3.25,
"max": 26.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1144.0,
"min": 143.0,
"max": 1392.0,
"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": "1703502591",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703503052"
},
"total": 460.67626434199997,
"count": 1,
"self": 0.4461915269998826,
"children": {
"run_training.setup": {
"total": 0.0510510050000903,
"count": 1,
"self": 0.0510510050000903
},
"TrainerController.start_learning": {
"total": 460.17902181,
"count": 1,
"self": 0.62784774099282,
"children": {
"TrainerController._reset_env": {
"total": 3.5107919950000905,
"count": 1,
"self": 3.5107919950000905
},
"TrainerController.advance": {
"total": 455.94239920900714,
"count": 18199,
"self": 0.3040284470039296,
"children": {
"env_step": {
"total": 455.6383707620032,
"count": 18199,
"self": 304.03030750799985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.29555547600035,
"count": 18199,
"self": 1.5481738949949886,
"children": {
"TorchPolicy.evaluate": {
"total": 149.74738158100536,
"count": 18199,
"self": 149.74738158100536
}
}
},
"workers": {
"total": 0.31250777800300966,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.89101768401065,
"count": 18199,
"is_parallel": true,
"self": 222.83901818900767,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005337412000017139,
"count": 1,
"is_parallel": true,
"self": 0.004032773000062662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013046389999544772,
"count": 10,
"is_parallel": true,
"self": 0.0013046389999544772
}
}
},
"UnityEnvironment.step": {
"total": 0.06891750800014051,
"count": 1,
"is_parallel": true,
"self": 0.0006953130002784746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036074499985261355,
"count": 1,
"is_parallel": true,
"self": 0.00036074499985261355
},
"communicator.exchange": {
"total": 0.06578478400001586,
"count": 1,
"is_parallel": true,
"self": 0.06578478400001586
},
"steps_from_proto": {
"total": 0.0020766659999935655,
"count": 1,
"is_parallel": true,
"self": 0.00044275900017964887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016339069998139166,
"count": 10,
"is_parallel": true,
"self": 0.0016339069998139166
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.05199949500297,
"count": 18198,
"is_parallel": true,
"self": 10.995739893004156,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.420467695999605,
"count": 18198,
"is_parallel": true,
"self": 5.420467695999605
},
"communicator.exchange": {
"total": 185.7388930589948,
"count": 18198,
"is_parallel": true,
"self": 185.7388930589948
},
"steps_from_proto": {
"total": 33.89689884700442,
"count": 18198,
"is_parallel": true,
"self": 6.511562485038894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.38533636196553,
"count": 181980,
"is_parallel": true,
"self": 27.38533636196553
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012827499995182734,
"count": 1,
"self": 0.00012827499995182734,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.4640106718625,
"count": 697297,
"is_parallel": true,
"self": 14.01282008984208,
"children": {
"process_trajectory": {
"total": 249.67662541302093,
"count": 697297,
"is_parallel": true,
"self": 249.17946226302115,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4971631499997784,
"count": 4,
"is_parallel": true,
"self": 0.4971631499997784
}
}
},
"_update_policy": {
"total": 186.77456516899952,
"count": 90,
"is_parallel": true,
"self": 58.66391408500135,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.11065108399816,
"count": 4587,
"is_parallel": true,
"self": 128.11065108399816
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09785458999999719,
"count": 1,
"self": 0.0010076259998186288,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09684696400017856,
"count": 1,
"self": 0.09684696400017856
}
}
}
}
}
}
}