Brain33's picture
First Push
8551d07 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8450980186462402,
"min": 0.8450980186462402,
"max": 2.8485777378082275,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8031.8115234375,
"min": 8031.8115234375,
"max": 29078.28125,
"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": 12.658498764038086,
"min": 0.45209991931915283,
"max": 12.658498764038086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.4072265625,
"min": 87.70738220214844,
"max": 2554.707275390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06912657877129438,
"min": 0.06568867294717004,
"max": 0.07569679805173483,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27650631508517753,
"min": 0.26275469178868016,
"max": 0.36725830876236487,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.190926135535918,
"min": 0.1389164570513565,
"max": 0.2658611365100917,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.763704542143672,
"min": 0.555665828205426,
"max": 1.327977391142471,
"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": 25.204545454545453,
"min": 4.045454545454546,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 178.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 4.045454545454546,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 178.0,
"max": 1381.0,
"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": "1753338516",
"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 --torch-device=cuda --force",
"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": "1753338947"
},
"total": 430.78109415400013,
"count": 1,
"self": 0.4242091450003045,
"children": {
"run_training.setup": {
"total": 0.020808940999813785,
"count": 1,
"self": 0.020808940999813785
},
"TrainerController.start_learning": {
"total": 430.336076068,
"count": 1,
"self": 0.3822449260005669,
"children": {
"TrainerController._reset_env": {
"total": 2.035707805000129,
"count": 1,
"self": 2.035707805000129
},
"TrainerController.advance": {
"total": 427.8375330529991,
"count": 18192,
"self": 0.4081302340100592,
"children": {
"env_step": {
"total": 308.20373723998387,
"count": 18192,
"self": 235.59063459597928,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.39495919199362,
"count": 18192,
"self": 1.2936011620006411,
"children": {
"TorchPolicy.evaluate": {
"total": 71.10135802999298,
"count": 18192,
"self": 71.10135802999298
}
}
},
"workers": {
"total": 0.2181434520109633,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 428.77589784800557,
"count": 18192,
"is_parallel": true,
"self": 222.42483368701141,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023375830000986753,
"count": 1,
"is_parallel": true,
"self": 0.0007428759997765155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015947070003221597,
"count": 10,
"is_parallel": true,
"self": 0.0015947070003221597
}
}
},
"UnityEnvironment.step": {
"total": 0.036917336999977124,
"count": 1,
"is_parallel": true,
"self": 0.0006134749999091582,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046089700003904,
"count": 1,
"is_parallel": true,
"self": 0.00046089700003904
},
"communicator.exchange": {
"total": 0.03391676000001098,
"count": 1,
"is_parallel": true,
"self": 0.03391676000001098
},
"steps_from_proto": {
"total": 0.0019262050000179443,
"count": 1,
"is_parallel": true,
"self": 0.0003737209999599145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015524840000580298,
"count": 10,
"is_parallel": true,
"self": 0.0015524840000580298
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.35106416099416,
"count": 18191,
"is_parallel": true,
"self": 9.818348357988043,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.492821275021015,
"count": 18191,
"is_parallel": true,
"self": 5.492821275021015
},
"communicator.exchange": {
"total": 158.7701796129927,
"count": 18191,
"is_parallel": true,
"self": 158.7701796129927
},
"steps_from_proto": {
"total": 32.26971491499239,
"count": 18191,
"is_parallel": true,
"self": 5.686173442999689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.583541471992703,
"count": 181910,
"is_parallel": true,
"self": 26.583541471992703
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.22566557900518,
"count": 18192,
"self": 0.43809771201495096,
"children": {
"process_trajectory": {
"total": 26.052131766991124,
"count": 18192,
"self": 25.688414149991104,
"children": {
"RLTrainer._checkpoint": {
"total": 0.36371761700002025,
"count": 4,
"self": 0.36371761700002025
}
}
},
"_update_policy": {
"total": 92.7354360999991,
"count": 90,
"self": 37.77364969600103,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.961786403998076,
"count": 4587,
"self": 54.961786403998076
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.920001164369751e-07,
"count": 1,
"self": 8.920001164369751e-07
},
"TrainerController._save_models": {
"total": 0.08058939200009263,
"count": 1,
"self": 0.001003776000061407,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07958561600003122,
"count": 1,
"self": 0.07958561600003122
}
}
}
}
}
}
}