phatpt's picture
First Push
794c051
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.971858561038971,
"min": 0.9410493969917297,
"max": 2.865011692047119,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9332.7578125,
"min": 9332.7578125,
"max": 29340.5859375,
"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": 12.676454544067383,
"min": 0.405673623085022,
"max": 12.676454544067383,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2471.90869140625,
"min": 78.70068359375,
"max": 2571.1708984375,
"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.Losses.PolicyLoss.mean": {
"value": 0.06590427068216492,
"min": 0.06188564535392181,
"max": 0.07564409434031832,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2636170827286597,
"min": 0.24754258141568725,
"max": 0.3647614519275022,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20876609468284776,
"min": 0.11692633915934529,
"max": 0.2610524816840303,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.835064378731391,
"min": 0.46770535663738116,
"max": 1.2994663055036582,
"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": 25.113636363636363,
"min": 3.409090909090909,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 150.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.409090909090909,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 150.0,
"max": 1378.0,
"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": "1692759840",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692760308"
},
"total": 467.413547377,
"count": 1,
"self": 0.8567161229998419,
"children": {
"run_training.setup": {
"total": 0.042895531999988634,
"count": 1,
"self": 0.042895531999988634
},
"TrainerController.start_learning": {
"total": 466.51393572200016,
"count": 1,
"self": 0.5216907359993002,
"children": {
"TrainerController._reset_env": {
"total": 4.966458370999931,
"count": 1,
"self": 4.966458370999931
},
"TrainerController.advance": {
"total": 460.7660825160008,
"count": 18222,
"self": 0.2591662840044364,
"children": {
"env_step": {
"total": 460.50691623199634,
"count": 18222,
"self": 339.5565579959854,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.676796043006,
"count": 18222,
"self": 1.7097605450068158,
"children": {
"TorchPolicy.evaluate": {
"total": 118.96703549799918,
"count": 18222,
"self": 118.96703549799918
}
}
},
"workers": {
"total": 0.2735621930049774,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.77123362300586,
"count": 18222,
"is_parallel": true,
"self": 217.3888715480049,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005914801000017178,
"count": 1,
"is_parallel": true,
"self": 0.004331719000219891,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015830819997972867,
"count": 10,
"is_parallel": true,
"self": 0.0015830819997972867
}
}
},
"UnityEnvironment.step": {
"total": 0.08073198600004616,
"count": 1,
"is_parallel": true,
"self": 0.0031670660001736906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042119299996556947,
"count": 1,
"is_parallel": true,
"self": 0.00042119299996556947
},
"communicator.exchange": {
"total": 0.06889356499993937,
"count": 1,
"is_parallel": true,
"self": 0.06889356499993937
},
"steps_from_proto": {
"total": 0.008250161999967531,
"count": 1,
"is_parallel": true,
"self": 0.0021454080000467,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006104753999920831,
"count": 10,
"is_parallel": true,
"self": 0.006104753999920831
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.38236207500097,
"count": 18221,
"is_parallel": true,
"self": 10.411060031996385,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.231370904002233,
"count": 18221,
"is_parallel": true,
"self": 5.231370904002233
},
"communicator.exchange": {
"total": 196.38750640101682,
"count": 18221,
"is_parallel": true,
"self": 196.38750640101682
},
"steps_from_proto": {
"total": 35.35242473798553,
"count": 18221,
"is_parallel": true,
"self": 6.386392319980132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.966032418005398,
"count": 182210,
"is_parallel": true,
"self": 28.966032418005398
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010273099996993551,
"count": 1,
"self": 0.00010273099996993551,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 457.45739310599345,
"count": 423319,
"is_parallel": true,
"self": 9.126308638016326,
"children": {
"process_trajectory": {
"total": 249.02565687497747,
"count": 423319,
"is_parallel": true,
"self": 247.8159306979777,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2097261769997658,
"count": 4,
"is_parallel": true,
"self": 1.2097261769997658
}
}
},
"_update_policy": {
"total": 199.30542759299965,
"count": 90,
"is_parallel": true,
"self": 81.11374653599626,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.1916810570034,
"count": 4587,
"is_parallel": true,
"self": 118.1916810570034
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2596013680001761,
"count": 1,
"self": 0.0011548830002539034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2584464849999222,
"count": 1,
"self": 0.2584464849999222
}
}
}
}
}
}
}