Sweigalytics's picture
First Push
625b4e0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9006370306015015,
"min": 0.9006370306015015,
"max": 2.8460676670074463,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8559.654296875,
"min": 8559.654296875,
"max": 29052.658203125,
"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": 12.42103099822998,
"min": 0.3159210681915283,
"max": 12.42103099822998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2422.10107421875,
"min": 61.2886848449707,
"max": 2508.90869140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07339541248816828,
"min": 0.0627708344324549,
"max": 0.07831481398270447,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2935816499526731,
"min": 0.2510833377298196,
"max": 0.38275808463895733,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19267069263493314,
"min": 0.1297624636231465,
"max": 0.276750143325212,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7706827705397326,
"min": 0.519049854492586,
"max": 1.3633766668099982,
"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": 24.65909090909091,
"min": 3.5,
"max": 24.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1085.0,
"min": 154.0,
"max": 1351.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.65909090909091,
"min": 3.5,
"max": 24.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1085.0,
"min": 154.0,
"max": 1351.0,
"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": "1771535335",
"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": "1771535810"
},
"total": 474.94312076899996,
"count": 1,
"self": 0.7491299439998329,
"children": {
"run_training.setup": {
"total": 0.025474356000131593,
"count": 1,
"self": 0.025474356000131593
},
"TrainerController.start_learning": {
"total": 474.168516469,
"count": 1,
"self": 0.38325915000586974,
"children": {
"TrainerController._reset_env": {
"total": 2.9034936019997986,
"count": 1,
"self": 2.9034936019997986
},
"TrainerController.advance": {
"total": 470.7622094959943,
"count": 18192,
"self": 0.3995228809847049,
"children": {
"env_step": {
"total": 345.7818907119952,
"count": 18192,
"self": 269.6364973270047,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.90050874000667,
"count": 18192,
"self": 1.3357678330078215,
"children": {
"TorchPolicy.evaluate": {
"total": 74.56474090699885,
"count": 18192,
"self": 74.56474090699885
}
}
},
"workers": {
"total": 0.2448846449838129,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.0696086579792,
"count": 18192,
"is_parallel": true,
"self": 235.47465145496835,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003207254000017201,
"count": 1,
"is_parallel": true,
"self": 0.0017668580005647527,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014403959994524485,
"count": 10,
"is_parallel": true,
"self": 0.0014403959994524485
}
}
},
"UnityEnvironment.step": {
"total": 0.03764030900015314,
"count": 1,
"is_parallel": true,
"self": 0.0006634790001953661,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044791999994231446,
"count": 1,
"is_parallel": true,
"self": 0.00044791999994231446
},
"communicator.exchange": {
"total": 0.03457013199999892,
"count": 1,
"is_parallel": true,
"self": 0.03457013199999892
},
"steps_from_proto": {
"total": 0.0019587780000165367,
"count": 1,
"is_parallel": true,
"self": 0.0003854409999348718,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015733370000816649,
"count": 10,
"is_parallel": true,
"self": 0.0015733370000816649
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.59495720301084,
"count": 18191,
"is_parallel": true,
"self": 11.007474639011434,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.922470286002181,
"count": 18191,
"is_parallel": true,
"self": 5.922470286002181
},
"communicator.exchange": {
"total": 179.8000259679941,
"count": 18191,
"is_parallel": true,
"self": 179.8000259679941
},
"steps_from_proto": {
"total": 39.86498631000313,
"count": 18191,
"is_parallel": true,
"self": 7.148783184010199,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.716203125992934,
"count": 181910,
"is_parallel": true,
"self": 32.716203125992934
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.5807959030144,
"count": 18192,
"self": 0.4904395670366739,
"children": {
"process_trajectory": {
"total": 28.122158193977384,
"count": 18192,
"self": 27.694418323977516,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42773986999986846,
"count": 4,
"self": 0.42773986999986846
}
}
},
"_update_policy": {
"total": 95.96819814200035,
"count": 90,
"self": 39.12521941699765,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.842978725002695,
"count": 4587,
"self": 56.842978725002695
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2739999419864034e-06,
"count": 1,
"self": 1.2739999419864034e-06
},
"TrainerController._save_models": {
"total": 0.119552947000102,
"count": 1,
"self": 0.0009499670002242055,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11860297999987779,
"count": 1,
"self": 0.11860297999987779
}
}
}
}
}
}
}