Tyraex's picture
Updated model
be590ed verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.8568122386932373,
"min": 1.8568122386932373,
"max": 2.8903470039367676,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 17810.54296875,
"min": 17775.48046875,
"max": 29759.01171875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 6.018762111663818,
"min": -0.017574388533830643,
"max": 6.018762111663818,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1233.84619140625,
"min": -3.602749824523926,
"max": 1233.84619140625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 17.672727272727272,
"min": 2.727272727272727,
"max": 18.181818181818183,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 972.0,
"min": 120.0,
"max": 972.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 17.672727272727272,
"min": 2.727272727272727,
"max": 18.181818181818183,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 972.0,
"min": 120.0,
"max": 972.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.035475623733418615,
"min": 0.03180414954922147,
"max": 0.03817954923768715,
"count": 15
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.035475623733418615,
"min": 0.03180414954922147,
"max": 0.03817954923768715,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3183900256020327,
"min": 0.08703206747304648,
"max": 0.3183900256020327,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3183900256020327,
"min": 0.08703206747304648,
"max": 0.3183900256020327,
"count": 15
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0176989823999964e-06,
"min": 1.0176989823999964e-06,
"max": 9.341760658240001e-05,
"count": 15
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0176989823999964e-06,
"min": 1.0176989823999964e-06,
"max": 9.341760658240001e-05,
"count": 15
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000003,
"min": 0.10101760000000003,
"max": 0.19341760000000005,
"count": 15
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10101760000000003,
"min": 0.10101760000000003,
"max": 0.19341760000000005,
"count": 15
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.077823999999984e-05,
"min": 6.077823999999984e-05,
"max": 0.004671538240000001,
"count": 15
},
"SnowballTarget.Policy.Beta.sum": {
"value": 6.077823999999984e-05,
"min": 6.077823999999984e-05,
"max": 0.004671538240000001,
"count": 15
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1760689714",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
"command_line_arguments": "/local_scratch/ahmohame/MyRLProj/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1760690960"
},
"total": 1246.1255109719932,
"count": 1,
"self": 0.374010790954344,
"children": {
"run_training.setup": {
"total": 0.02128842705860734,
"count": 1,
"self": 0.02128842705860734
},
"TrainerController.start_learning": {
"total": 1245.7302117539803,
"count": 1,
"self": 0.6739412506576627,
"children": {
"TrainerController._reset_env": {
"total": 2.9158263229765,
"count": 1,
"self": 2.9158263229765
},
"TrainerController.advance": {
"total": 1242.0460719174007,
"count": 45464,
"self": 0.6814981006318703,
"children": {
"env_step": {
"total": 1054.3282872018171,
"count": 45464,
"self": 919.0131197725423,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.8636818312807,
"count": 45464,
"self": 2.2304799418197945,
"children": {
"TorchPolicy.evaluate": {
"total": 132.6332018894609,
"count": 45464,
"self": 132.6332018894609
}
}
},
"workers": {
"total": 0.45148559799417853,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1243.1112274315674,
"count": 45464,
"is_parallel": true,
"self": 398.501711131772,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00440782296936959,
"count": 1,
"is_parallel": true,
"self": 0.0011371220462024212,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003270700923167169,
"count": 10,
"is_parallel": true,
"self": 0.003270700923167169
}
}
},
"UnityEnvironment.step": {
"total": 0.04261121794115752,
"count": 1,
"is_parallel": true,
"self": 0.0009077248396351933,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006594400620087981,
"count": 1,
"is_parallel": true,
"self": 0.0006594400620087981
},
"communicator.exchange": {
"total": 0.03817833599168807,
"count": 1,
"is_parallel": true,
"self": 0.03817833599168807
},
"steps_from_proto": {
"total": 0.0028657170478254557,
"count": 1,
"is_parallel": true,
"self": 0.0005921600386500359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00227355700917542,
"count": 10,
"is_parallel": true,
"self": 0.00227355700917542
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 844.6095162997954,
"count": 45463,
"is_parallel": true,
"self": 35.7958256395068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.017438556067646,
"count": 45463,
"is_parallel": true,
"self": 21.017438556067646
},
"communicator.exchange": {
"total": 676.2517781199422,
"count": 45463,
"is_parallel": true,
"self": 676.2517781199422
},
"steps_from_proto": {
"total": 111.54447398427874,
"count": 45463,
"is_parallel": true,
"self": 21.141052892548032,
"children": {
"_process_rank_one_or_two_observation": {
"total": 90.4034210917307,
"count": 454630,
"is_parallel": true,
"self": 90.4034210917307
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 187.03628661495168,
"count": 45464,
"self": 0.7960933083668351,
"children": {
"process_trajectory": {
"total": 50.32543419068679,
"count": 45464,
"self": 49.403155541745946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9222786489408463,
"count": 10,
"self": 0.9222786489408463
}
}
},
"_update_policy": {
"total": 135.91475911589805,
"count": 15,
"self": 79.53988587856293,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.37487323733512,
"count": 2880,
"self": 56.37487323733512
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.719507604837418e-07,
"count": 1,
"self": 8.719507604837418e-07
},
"TrainerController._save_models": {
"total": 0.0943713909946382,
"count": 1,
"self": 0.0012160909827798605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09315530001185834,
"count": 1,
"self": 0.09315530001185834
}
}
}
}
}
}
}