Johnsonin's picture
First Push
9b81970 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.819754958152771,
"min": 0.8088752627372742,
"max": 2.86527156829834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7790.951171875,
"min": 7790.951171875,
"max": 29248.69140625,
"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": 12.893610954284668,
"min": 0.3824966251850128,
"max": 12.893610954284668,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2514.254150390625,
"min": 74.204345703125,
"max": 2629.37744140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0715748869778883,
"min": 0.06471920140434569,
"max": 0.07295726555052633,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2862995479115532,
"min": 0.2635020139160927,
"max": 0.36478632775263165,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19104494731508048,
"min": 0.13845035546532303,
"max": 0.31101202526513266,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7641797892603219,
"min": 0.5538014218612921,
"max": 1.5550601263256634,
"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": 25.136363636363637,
"min": 3.7954545454545454,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 167.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.7954545454545454,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 167.0,
"max": 1396.0,
"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": "1751498050",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751498491"
},
"total": 440.7123096549999,
"count": 1,
"self": 0.39002986299965414,
"children": {
"run_training.setup": {
"total": 0.028018601999974635,
"count": 1,
"self": 0.028018601999974635
},
"TrainerController.start_learning": {
"total": 440.29426119000027,
"count": 1,
"self": 0.39178255501497006,
"children": {
"TrainerController._reset_env": {
"total": 3.1044391440000254,
"count": 1,
"self": 3.1044391440000254
},
"TrainerController.advance": {
"total": 436.71583887898555,
"count": 18192,
"self": 0.41024163996212337,
"children": {
"env_step": {
"total": 316.39410831699433,
"count": 18192,
"self": 243.54898806399,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.61658315698696,
"count": 18192,
"self": 1.3071297899905403,
"children": {
"TorchPolicy.evaluate": {
"total": 71.30945336699642,
"count": 18192,
"self": 71.30945336699642
}
}
},
"workers": {
"total": 0.22853709601736227,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.7880902690167,
"count": 18192,
"is_parallel": true,
"self": 225.5286873059349,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005356477999839626,
"count": 1,
"is_parallel": true,
"self": 0.003946860999803903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014096170000357233,
"count": 10,
"is_parallel": true,
"self": 0.0014096170000357233
}
}
},
"UnityEnvironment.step": {
"total": 0.03601250299993808,
"count": 1,
"is_parallel": true,
"self": 0.0006285810002282233,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041715899988048477,
"count": 1,
"is_parallel": true,
"self": 0.00041715899988048477
},
"communicator.exchange": {
"total": 0.03302891999987878,
"count": 1,
"is_parallel": true,
"self": 0.03302891999987878
},
"steps_from_proto": {
"total": 0.0019378429999505897,
"count": 1,
"is_parallel": true,
"self": 0.00037174299995967885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015660999999909109,
"count": 10,
"is_parallel": true,
"self": 0.0015660999999909109
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.2594029630818,
"count": 18191,
"is_parallel": true,
"self": 9.930555755101977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.564687964983477,
"count": 18191,
"is_parallel": true,
"self": 5.564687964983477
},
"communicator.exchange": {
"total": 164.93797299999687,
"count": 18191,
"is_parallel": true,
"self": 164.93797299999687
},
"steps_from_proto": {
"total": 32.82618624299948,
"count": 18191,
"is_parallel": true,
"self": 5.9536057820412225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.87258046095826,
"count": 181910,
"is_parallel": true,
"self": 26.87258046095826
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.9114889220291,
"count": 18192,
"self": 0.47297145998140877,
"children": {
"process_trajectory": {
"total": 26.725953207049088,
"count": 18192,
"self": 26.32991687804929,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39603632899979857,
"count": 4,
"self": 0.39603632899979857
}
}
},
"_update_policy": {
"total": 92.7125642549986,
"count": 90,
"self": 38.08335925599704,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.62920499900156,
"count": 4587,
"self": 54.62920499900156
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0369999472459313e-06,
"count": 1,
"self": 1.0369999472459313e-06
},
"TrainerController._save_models": {
"total": 0.08219957499977681,
"count": 1,
"self": 0.0008460989997729484,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08135347600000387,
"count": 1,
"self": 0.08135347600000387
}
}
}
}
}
}
}