Hrou's picture
First Push
1c67062 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6213773488998413,
"min": 0.6213773488998413,
"max": 2.843733072280884,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6397.701171875,
"min": 6113.88818359375,
"max": 29028.826171875,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.359021186828613,
"min": 0.4805935025215149,
"max": 13.435613632202148,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2725.240234375,
"min": 93.23513793945312,
"max": 2754.30078125,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06437358227436633,
"min": 0.06318966928276995,
"max": 0.07418257988605297,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3218679113718317,
"min": 0.2527586771310798,
"max": 0.36505840468453243,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2094956780181212,
"min": 0.13927282213105582,
"max": 0.27264900023446365,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.047478390090606,
"min": 0.5570912885242233,
"max": 1.3411285523690428,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.288098237333331e-06,
"min": 5.288098237333331e-06,
"max": 0.00029458800180399996,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.6440491186666655e-05,
"min": 2.6440491186666655e-05,
"max": 0.0014234400255199997,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.198196,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5088133333333333,
"min": 0.42025066666666666,
"max": 0.97448,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666662e-05,
"min": 9.795706666666662e-05,
"max": 0.0049099804000000006,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004897853333333331,
"min": 0.0004897853333333331,
"max": 0.023726551999999998,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.963636363636365,
"min": 3.8636363636363638,
"max": 26.522727272727273,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1428.0,
"min": 170.0,
"max": 1455.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.963636363636365,
"min": 3.8636363636363638,
"max": 26.522727272727273,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1428.0,
"min": 170.0,
"max": 1455.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740098740",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740099592"
},
"total": 851.383132031,
"count": 1,
"self": 0.542016182999987,
"children": {
"run_training.setup": {
"total": 0.034316627000066546,
"count": 1,
"self": 0.034316627000066546
},
"TrainerController.start_learning": {
"total": 850.8067992209999,
"count": 1,
"self": 0.9045263399925716,
"children": {
"TrainerController._reset_env": {
"total": 3.5543770509999604,
"count": 1,
"self": 3.5543770509999604
},
"TrainerController.advance": {
"total": 846.2609781020072,
"count": 27328,
"self": 1.0388677060125246,
"children": {
"env_step": {
"total": 584.6941772029971,
"count": 27328,
"self": 495.4496216039827,
"children": {
"SubprocessEnvManager._take_step": {
"total": 88.67860312600772,
"count": 27328,
"self": 2.9233486470213847,
"children": {
"TorchPolicy.evaluate": {
"total": 85.75525447898633,
"count": 27328,
"self": 85.75525447898633
}
}
},
"workers": {
"total": 0.565952473006746,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 847.9390296939879,
"count": 27328,
"is_parallel": true,
"self": 419.2735723219748,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007745441999986724,
"count": 1,
"is_parallel": true,
"self": 0.005389997999827756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023554440001589683,
"count": 10,
"is_parallel": true,
"self": 0.0023554440001589683
}
}
},
"UnityEnvironment.step": {
"total": 0.07162547899997662,
"count": 1,
"is_parallel": true,
"self": 0.0007477630000494173,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047760399991148006,
"count": 1,
"is_parallel": true,
"self": 0.00047760399991148006
},
"communicator.exchange": {
"total": 0.06825256199999785,
"count": 1,
"is_parallel": true,
"self": 0.06825256199999785
},
"steps_from_proto": {
"total": 0.0021475500000178727,
"count": 1,
"is_parallel": true,
"self": 0.00041917999999441236,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017283700000234603,
"count": 10,
"is_parallel": true,
"self": 0.0017283700000234603
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 428.66545737201307,
"count": 27327,
"is_parallel": true,
"self": 20.647142027011682,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.046566649999136,
"count": 27327,
"is_parallel": true,
"self": 11.046566649999136
},
"communicator.exchange": {
"total": 335.22841942199534,
"count": 27327,
"is_parallel": true,
"self": 335.22841942199534
},
"steps_from_proto": {
"total": 61.74332927300691,
"count": 27327,
"is_parallel": true,
"self": 11.798547389018381,
"children": {
"_process_rank_one_or_two_observation": {
"total": 49.944781883988526,
"count": 273270,
"is_parallel": true,
"self": 49.944781883988526
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 260.5279331929976,
"count": 27328,
"self": 1.1534877840255149,
"children": {
"process_trajectory": {
"total": 46.273652702970935,
"count": 27328,
"self": 45.6078580259707,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6657946770002354,
"count": 6,
"self": 0.6657946770002354
}
}
},
"_update_policy": {
"total": 213.10079270600113,
"count": 136,
"self": 75.08534320100262,
"children": {
"TorchPPOOptimizer.update": {
"total": 138.01544950499851,
"count": 6933,
"self": 138.01544950499851
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0280000424245372e-06,
"count": 1,
"self": 1.0280000424245372e-06
},
"TrainerController._save_models": {
"total": 0.08691670000007434,
"count": 1,
"self": 0.0012328360000992689,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08568386399997507,
"count": 1,
"self": 0.08568386399997507
}
}
}
}
}
}
}