dimgalli's picture
First Push
63bc1ff verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6275211572647095,
"min": 0.615613579750061,
"max": 2.847135543823242,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5963.9609375,
"min": 5963.9609375,
"max": 29063.55859375,
"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": 12.941213607788086,
"min": 0.4888489246368408,
"max": 12.941213607788086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.53662109375,
"min": 94.8366928100586,
"max": 2624.315673828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07690387904671404,
"min": 0.06468890766040668,
"max": 0.07690387904671404,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3076155161868562,
"min": 0.2587556306416267,
"max": 0.37172995619338883,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19710416127653682,
"min": 0.13487873897960811,
"max": 0.2922748357203661,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7884166451061473,
"min": 0.5395149559184325,
"max": 1.4283574021914425,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.772727272727273,
"min": 3.6136363636363638,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 159.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.6136363636363638,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 159.0,
"max": 1407.0,
"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": "1765968619",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765969090"
},
"total": 470.2552054659999,
"count": 1,
"self": 0.45033554099995854,
"children": {
"run_training.setup": {
"total": 0.027195860999995602,
"count": 1,
"self": 0.027195860999995602
},
"TrainerController.start_learning": {
"total": 469.77767406399994,
"count": 1,
"self": 0.41880778800725693,
"children": {
"TrainerController._reset_env": {
"total": 2.942142106999995,
"count": 1,
"self": 2.942142106999995
},
"TrainerController.advance": {
"total": 466.3265833179926,
"count": 18192,
"self": 0.41281071400203473,
"children": {
"env_step": {
"total": 342.45004738699083,
"count": 18192,
"self": 267.74070017199926,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.47174547398936,
"count": 18192,
"self": 1.3120633639854304,
"children": {
"TorchPolicy.evaluate": {
"total": 73.15968211000393,
"count": 18192,
"self": 73.15968211000393
}
}
},
"workers": {
"total": 0.23760174100220866,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 467.9046546200001,
"count": 18192,
"is_parallel": true,
"self": 232.95241466399,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005100246000097286,
"count": 1,
"is_parallel": true,
"self": 0.0037450470001658687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013551989999314173,
"count": 10,
"is_parallel": true,
"self": 0.0013551989999314173
}
}
},
"UnityEnvironment.step": {
"total": 0.03794799199999943,
"count": 1,
"is_parallel": true,
"self": 0.0007153740001513142,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003992179999841028,
"count": 1,
"is_parallel": true,
"self": 0.0003992179999841028
},
"communicator.exchange": {
"total": 0.03476113699991856,
"count": 1,
"is_parallel": true,
"self": 0.03476113699991856
},
"steps_from_proto": {
"total": 0.002072262999945451,
"count": 1,
"is_parallel": true,
"self": 0.000440905999653296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016313570002921551,
"count": 10,
"is_parallel": true,
"self": 0.0016313570002921551
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.9522399560101,
"count": 18191,
"is_parallel": true,
"self": 10.86074408601587,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.787397353999836,
"count": 18191,
"is_parallel": true,
"self": 5.787397353999836
},
"communicator.exchange": {
"total": 179.36418673798505,
"count": 18191,
"is_parallel": true,
"self": 179.36418673798505
},
"steps_from_proto": {
"total": 38.93991177800933,
"count": 18191,
"is_parallel": true,
"self": 6.94521862297961,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.994693155029722,
"count": 181910,
"is_parallel": true,
"self": 31.994693155029722
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.4637252169997,
"count": 18192,
"self": 0.5014663319931287,
"children": {
"process_trajectory": {
"total": 26.63656447700623,
"count": 18192,
"self": 26.123658773006127,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5129057040001044,
"count": 4,
"self": 0.5129057040001044
}
}
},
"_update_policy": {
"total": 96.32569440800034,
"count": 90,
"self": 39.83614988399813,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.48954452400221,
"count": 4587,
"self": 56.48954452400221
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.120001323026372e-07,
"count": 1,
"self": 9.120001323026372e-07
},
"TrainerController._save_models": {
"total": 0.0901399389999824,
"count": 1,
"self": 0.0007521879999785597,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08938775100000385,
"count": 1,
"self": 0.08938775100000385
}
}
}
}
}
}
}