alexillovsky's picture
First Snowball Push
ec973d1 verified
Raw
History Blame Contribute Delete
17.6 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8254396319389343,
"min": 0.8254396319389343,
"max": 2.8353211879730225,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7844.97802734375,
"min": 7844.97802734375,
"max": 28942.958984375,
"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": 13.14991283416748,
"min": 0.2946140170097351,
"max": 13.14991283416748,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2564.23291015625,
"min": 57.15511703491211,
"max": 2656.83837890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06977963484093254,
"min": 0.06407254887493692,
"max": 0.07677583466848933,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27911853936373016,
"min": 0.25686751531426194,
"max": 0.3838791733424467,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17778977087023212,
"min": 0.10777785875218208,
"max": 0.2922348934061387,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7111590834809285,
"min": 0.43111143500872834,
"max": 1.4611744670306934,
"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": 25.954545454545453,
"min": 3.2954545454545454,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 145.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 3.2954545454545454,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 145.0,
"max": 1423.0,
"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": "1776181439",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./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": "1776181898"
},
"total": 459.31226147600023,
"count": 1,
"self": 0.6366751510001905,
"children": {
"run_training.setup": {
"total": 0.022965910000039003,
"count": 1,
"self": 0.022965910000039003
},
"TrainerController.start_learning": {
"total": 458.652620415,
"count": 1,
"self": 0.3950345249786551,
"children": {
"TrainerController._reset_env": {
"total": 3.5997677230000136,
"count": 1,
"self": 3.5997677230000136
},
"TrainerController.advance": {
"total": 454.5387450490214,
"count": 18192,
"self": 0.4044544869807396,
"children": {
"env_step": {
"total": 332.61953719801795,
"count": 18192,
"self": 260.150052957006,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.23453670801928,
"count": 18192,
"self": 1.2944766430259733,
"children": {
"TorchPolicy.evaluate": {
"total": 70.9400600649933,
"count": 18192,
"self": 70.9400600649933
}
}
},
"workers": {
"total": 0.23494753299269178,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.36430846997996,
"count": 18192,
"is_parallel": true,
"self": 227.88455726597454,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005075077999890709,
"count": 1,
"is_parallel": true,
"self": 0.0034951470001942653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001579930999696444,
"count": 10,
"is_parallel": true,
"self": 0.001579930999696444
}
}
},
"UnityEnvironment.step": {
"total": 0.03869049400009317,
"count": 1,
"is_parallel": true,
"self": 0.0006622380001317651,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043880299995180394,
"count": 1,
"is_parallel": true,
"self": 0.00043880299995180394
},
"communicator.exchange": {
"total": 0.03546779099997366,
"count": 1,
"is_parallel": true,
"self": 0.03546779099997366
},
"steps_from_proto": {
"total": 0.00212166200003594,
"count": 1,
"is_parallel": true,
"self": 0.0004171100003986794,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017045519996372605,
"count": 10,
"is_parallel": true,
"self": 0.0017045519996372605
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.47975120400542,
"count": 18191,
"is_parallel": true,
"self": 10.574333513025522,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.685623187971032,
"count": 18191,
"is_parallel": true,
"self": 5.685623187971032
},
"communicator.exchange": {
"total": 173.5446066190225,
"count": 18191,
"is_parallel": true,
"self": 173.5446066190225
},
"steps_from_proto": {
"total": 38.67518788398638,
"count": 18191,
"is_parallel": true,
"self": 6.836687329967162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.83850055401922,
"count": 181910,
"is_parallel": true,
"self": 31.83850055401922
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.51475336402268,
"count": 18192,
"self": 0.46683699100822196,
"children": {
"process_trajectory": {
"total": 27.086405616014645,
"count": 18192,
"self": 26.642957702015337,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4434479139993073,
"count": 4,
"self": 0.4434479139993073
}
}
},
"_update_policy": {
"total": 93.96151075699981,
"count": 90,
"self": 38.36234354500925,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.59916721199056,
"count": 4587,
"self": 55.59916721199056
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7490001482656226e-06,
"count": 1,
"self": 1.7490001482656226e-06
},
"TrainerController._save_models": {
"total": 0.11907136899981197,
"count": 1,
"self": 0.0010272779995830206,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11804409100022895,
"count": 1,
"self": 0.11804409100022895
}
}
}
}
}
}
}