RitsRits's picture
First Push
34363ab verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8079862594604492,
"min": 0.8079862594604492,
"max": 2.862421989440918,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7714.65283203125,
"min": 7714.65283203125,
"max": 29314.064453125,
"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": 12.78941535949707,
"min": 0.3652503490447998,
"max": 12.78941535949707,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.93603515625,
"min": 70.85856628417969,
"max": 2584.745849609375,
"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.Losses.PolicyLoss.mean": {
"value": 0.06951184752859475,
"min": 0.06354298937755327,
"max": 0.07528207479627586,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.278047390114379,
"min": 0.25846195529718935,
"max": 0.35531129854429955,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19664009353693793,
"min": 0.13434751971405656,
"max": 0.3150325459884662,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7865603741477517,
"min": 0.5373900788562262,
"max": 1.3772880920008117,
"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.CumulativeReward.mean": {
"value": 25.568181818181817,
"min": 3.909090909090909,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 172.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.909090909090909,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 172.0,
"max": 1378.0,
"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": "1712067491",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712067962"
},
"total": 470.32085936,
"count": 1,
"self": 0.6143948629999159,
"children": {
"run_training.setup": {
"total": 0.057170986000073754,
"count": 1,
"self": 0.057170986000073754
},
"TrainerController.start_learning": {
"total": 469.649293511,
"count": 1,
"self": 0.5935337059770518,
"children": {
"TrainerController._reset_env": {
"total": 2.649582971999962,
"count": 1,
"self": 2.649582971999962
},
"TrainerController.advance": {
"total": 466.30542744102286,
"count": 18198,
"self": 0.2907512260189833,
"children": {
"env_step": {
"total": 466.0146762150039,
"count": 18198,
"self": 299.8724527110039,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.84116397801017,
"count": 18198,
"self": 1.5315709990104551,
"children": {
"TorchPolicy.evaluate": {
"total": 164.30959297899972,
"count": 18198,
"self": 164.30959297899972
}
}
},
"workers": {
"total": 0.30105952598978547,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.48451488899445,
"count": 18198,
"is_parallel": true,
"self": 234.59260147398095,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007415891999926316,
"count": 1,
"is_parallel": true,
"self": 0.003519816000107312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003896075999819004,
"count": 10,
"is_parallel": true,
"self": 0.003896075999819004
}
}
},
"UnityEnvironment.step": {
"total": 0.03929107799990561,
"count": 1,
"is_parallel": true,
"self": 0.0006434599997646728,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000399484000126904,
"count": 1,
"is_parallel": true,
"self": 0.000399484000126904
},
"communicator.exchange": {
"total": 0.036044527000058224,
"count": 1,
"is_parallel": true,
"self": 0.036044527000058224
},
"steps_from_proto": {
"total": 0.0022036069999558094,
"count": 1,
"is_parallel": true,
"self": 0.0004233190004470089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017802879995088006,
"count": 10,
"is_parallel": true,
"self": 0.0017802879995088006
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.8919134150135,
"count": 18197,
"is_parallel": true,
"self": 10.671761028032051,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.764898747997904,
"count": 18197,
"is_parallel": true,
"self": 5.764898747997904
},
"communicator.exchange": {
"total": 181.14930558098285,
"count": 18197,
"is_parallel": true,
"self": 181.14930558098285
},
"steps_from_proto": {
"total": 36.305948058000695,
"count": 18197,
"is_parallel": true,
"self": 6.821085672983372,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.484862385017323,
"count": 181970,
"is_parallel": true,
"self": 29.484862385017323
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017250400014745537,
"count": 1,
"self": 0.00017250400014745537,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 460.33392468506486,
"count": 697021,
"is_parallel": true,
"self": 15.13244031604654,
"children": {
"process_trajectory": {
"total": 255.013979949018,
"count": 697021,
"is_parallel": true,
"self": 254.05329420501766,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9606857440003296,
"count": 4,
"is_parallel": true,
"self": 0.9606857440003296
}
}
},
"_update_policy": {
"total": 190.18750442000032,
"count": 90,
"is_parallel": true,
"self": 52.89198301399733,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.295521406003,
"count": 4584,
"is_parallel": true,
"self": 137.295521406003
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10057688799997777,
"count": 1,
"self": 0.0009585600000718841,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09961832799990589,
"count": 1,
"self": 0.09961832799990589
}
}
}
}
}
}
}