Dorian-T's picture
First Push
883fe3a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9485664963722229,
"min": 0.943446934223175,
"max": 2.8646278381347656,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9056.9130859375,
"min": 9056.9130859375,
"max": 29368.1640625,
"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": 12.666397094726562,
"min": 0.37961122393608093,
"max": 12.666397094726562,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2469.947509765625,
"min": 73.64457702636719,
"max": 2552.21630859375,
"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": 24.954545454545453,
"min": 3.227272727272727,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 142.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.227272727272727,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 142.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06686514878417846,
"min": 0.061948582749227724,
"max": 0.07444372737882077,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26746059513671383,
"min": 0.26746059513671383,
"max": 0.37179791660038936,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21083655190088002,
"min": 0.11415677108601027,
"max": 0.2928545025276722,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8433462076035201,
"min": 0.4566270843440411,
"max": 1.464272512638361,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.00029184900271699997,
"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": 0.19728300000000004,
"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": 0.0048644217,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"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": "1727075322",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727075846"
},
"total": 524.25037943,
"count": 1,
"self": 0.5318545579999636,
"children": {
"run_training.setup": {
"total": 0.06340707099997189,
"count": 1,
"self": 0.06340707099997189
},
"TrainerController.start_learning": {
"total": 523.655117801,
"count": 1,
"self": 0.75395623200518,
"children": {
"TrainerController._reset_env": {
"total": 2.3797320780000177,
"count": 1,
"self": 2.3797320780000177
},
"TrainerController.advance": {
"total": 520.4348667379946,
"count": 18201,
"self": 0.3973511209785556,
"children": {
"env_step": {
"total": 520.0375156170161,
"count": 18201,
"self": 403.53680930702717,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.1164411749952,
"count": 18201,
"self": 1.80987673698678,
"children": {
"TorchPolicy.evaluate": {
"total": 114.30656443800842,
"count": 18201,
"self": 114.30656443800842
}
}
},
"workers": {
"total": 0.3842651349937114,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 522.0758944630081,
"count": 18201,
"is_parallel": true,
"self": 240.480955836002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002450468999995792,
"count": 1,
"is_parallel": true,
"self": 0.0007332860000133223,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017171829999824695,
"count": 10,
"is_parallel": true,
"self": 0.0017171829999824695
}
}
},
"UnityEnvironment.step": {
"total": 0.046985392000010506,
"count": 1,
"is_parallel": true,
"self": 0.000849916000106532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042678399995565997,
"count": 1,
"is_parallel": true,
"self": 0.00042678399995565997
},
"communicator.exchange": {
"total": 0.04334974299996475,
"count": 1,
"is_parallel": true,
"self": 0.04334974299996475
},
"steps_from_proto": {
"total": 0.0023589489999835678,
"count": 1,
"is_parallel": true,
"self": 0.0004377169998406316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019212320001429362,
"count": 10,
"is_parallel": true,
"self": 0.0019212320001429362
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 281.5949386270061,
"count": 18200,
"is_parallel": true,
"self": 13.045421829005306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.635346239998512,
"count": 18200,
"is_parallel": true,
"self": 6.635346239998512
},
"communicator.exchange": {
"total": 220.72249058300082,
"count": 18200,
"is_parallel": true,
"self": 220.72249058300082
},
"steps_from_proto": {
"total": 41.19167997500148,
"count": 18200,
"is_parallel": true,
"self": 7.993513662986118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.19816631201536,
"count": 182000,
"is_parallel": true,
"self": 33.19816631201536
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0006511490000775666,
"count": 1,
"self": 0.0006511490000775666,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 514.5608568120097,
"count": 701962,
"is_parallel": true,
"self": 15.002933525997207,
"children": {
"process_trajectory": {
"total": 278.0997846330124,
"count": 701962,
"is_parallel": true,
"self": 277.17645015901235,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9233344740000575,
"count": 4,
"is_parallel": true,
"self": 0.9233344740000575
}
}
},
"_update_policy": {
"total": 221.45813865300005,
"count": 90,
"is_parallel": true,
"self": 65.14722218599559,
"children": {
"TorchPPOOptimizer.update": {
"total": 156.31091646700446,
"count": 4587,
"is_parallel": true,
"self": 156.31091646700446
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08591160399998898,
"count": 1,
"self": 0.0011777099999790153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08473389400000997,
"count": 1,
"self": 0.08473389400000997
}
}
}
}
}
}
}