Simple-Chop's picture
First Push
40b86d0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9184542298316956,
"min": 0.9184542298316956,
"max": 2.81669545173645,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8728.9892578125,
"min": 8728.9892578125,
"max": 28752.828125,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.427462577819824,
"min": 0.5085029602050781,
"max": 12.427462577819824,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2410.927734375,
"min": 98.64957427978516,
"max": 2502.2216796875,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0703852664925102,
"min": 0.06290164182924748,
"max": 0.074155039231318,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2815410659700408,
"min": 0.26876624569202107,
"max": 0.36516064702756884,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18249935371910825,
"min": 0.1505507866888508,
"max": 0.28534768879705785,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.729997414876433,
"min": 0.6022031467554032,
"max": 1.3428776874846102,
"count": 25
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.707394084800001e-06,
"min": 5.707394084800001e-06,
"max": 0.00029154889816479995,
"count": 25
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.2829576339200005e-05,
"min": 2.2829576339200005e-05,
"max": 0.0013987405106239998,
"count": 25
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10191520000000001,
"min": 0.10191520000000001,
"max": 0.19783520000000002,
"count": 25
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40766080000000005,
"min": 0.40766080000000005,
"max": 0.9693760000000002,
"count": 25
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00010556848000000002,
"min": 0.00010556848000000002,
"max": 0.004891976480000001,
"count": 25
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004222739200000001,
"min": 0.0004222739200000001,
"max": 0.023471862399999998,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.818181818181817,
"min": 4.181818181818182,
"max": 24.818181818181817,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1092.0,
"min": 184.0,
"max": 1345.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.818181818181817,
"min": 4.181818181818182,
"max": 24.818181818181817,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1092.0,
"min": 184.0,
"max": 1345.0,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1741646597",
"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": "1741647133"
},
"total": 536.3418992840001,
"count": 1,
"self": 0.4480895670000109,
"children": {
"run_training.setup": {
"total": 0.023027597000009337,
"count": 1,
"self": 0.023027597000009337
},
"TrainerController.start_learning": {
"total": 535.8707821200001,
"count": 1,
"self": 0.41214928602300915,
"children": {
"TrainerController._reset_env": {
"total": 3.2779800280000018,
"count": 1,
"self": 3.2779800280000018
},
"TrainerController.advance": {
"total": 532.0906523599771,
"count": 22728,
"self": 0.4531629109866344,
"children": {
"env_step": {
"total": 378.3638527900097,
"count": 22728,
"self": 287.2050876610082,
"children": {
"SubprocessEnvManager._take_step": {
"total": 90.90064846798941,
"count": 22728,
"self": 1.6165385640065324,
"children": {
"TorchPolicy.evaluate": {
"total": 89.28410990398288,
"count": 22728,
"self": 89.28410990398288
}
}
},
"workers": {
"total": 0.25811666101208175,
"count": 22728,
"self": 0.0,
"children": {
"worker_root": {
"total": 534.1588778859963,
"count": 22728,
"is_parallel": true,
"self": 282.0358986400065,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006503553000015927,
"count": 1,
"is_parallel": true,
"self": 0.004253432999803408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002250120000212519,
"count": 10,
"is_parallel": true,
"self": 0.002250120000212519
}
}
},
"UnityEnvironment.step": {
"total": 0.03561375300000691,
"count": 1,
"is_parallel": true,
"self": 0.0005574189997332724,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047396400009347417,
"count": 1,
"is_parallel": true,
"self": 0.00047396400009347417
},
"communicator.exchange": {
"total": 0.03271787900007439,
"count": 1,
"is_parallel": true,
"self": 0.03271787900007439
},
"steps_from_proto": {
"total": 0.0018644910001057724,
"count": 1,
"is_parallel": true,
"self": 0.0003908549999778188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014736360001279536,
"count": 10,
"is_parallel": true,
"self": 0.0014736360001279536
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.12297924598977,
"count": 22727,
"is_parallel": true,
"self": 12.031990192981311,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.717991021003172,
"count": 22727,
"is_parallel": true,
"self": 6.717991021003172
},
"communicator.exchange": {
"total": 193.77643469802263,
"count": 22727,
"is_parallel": true,
"self": 193.77643469802263
},
"steps_from_proto": {
"total": 39.59656333398266,
"count": 22727,
"is_parallel": true,
"self": 7.093466325957024,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.503097008025634,
"count": 227270,
"is_parallel": true,
"self": 32.503097008025634
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 153.27363665898076,
"count": 22728,
"self": 0.5002315519668628,
"children": {
"process_trajectory": {
"total": 33.87380536701437,
"count": 22728,
"self": 33.19855794301429,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6752474240000765,
"count": 5,
"self": 0.6752474240000765
}
}
},
"_update_policy": {
"total": 118.89959973999953,
"count": 113,
"self": 47.123057315981896,
"children": {
"TorchPPOOptimizer.update": {
"total": 71.77654242401763,
"count": 5760,
"self": 71.77654242401763
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3429998944047838e-06,
"count": 1,
"self": 1.3429998944047838e-06
},
"TrainerController._save_models": {
"total": 0.08999910300008196,
"count": 1,
"self": 0.0009554480000133481,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08904365500006861,
"count": 1,
"self": 0.08904365500006861
}
}
}
}
}
}
}