niltheory's picture
First Push
4160a30
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9453619718551636,
"min": 0.9064144492149353,
"max": 2.8615152835845947,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9047.1142578125,
"min": 9047.1142578125,
"max": 29430.68359375,
"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": 11.980561256408691,
"min": 0.4914911687374115,
"max": 11.980561256408691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2336.20947265625,
"min": 95.34928894042969,
"max": 2411.254638671875,
"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": 0.065632115441201,
"min": 0.06196921678652586,
"max": 0.0781425507839623,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.262528461764804,
"min": 0.2519367087846987,
"max": 0.39071275391981153,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19057177270160003,
"min": 0.12920897139701992,
"max": 0.2795422208659789,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7622870908064001,
"min": 0.5168358855880797,
"max": 1.256461565090599,
"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": 24.0,
"min": 3.6363636363636362,
"max": 24.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1056.0,
"min": 160.0,
"max": 1288.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.0,
"min": 3.6363636363636362,
"max": 24.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1056.0,
"min": 160.0,
"max": 1288.0,
"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": "1701148777",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701149391"
},
"total": 613.7299517649999,
"count": 1,
"self": 0.6415124529999048,
"children": {
"run_training.setup": {
"total": 0.059936709999988125,
"count": 1,
"self": 0.059936709999988125
},
"TrainerController.start_learning": {
"total": 613.028502602,
"count": 1,
"self": 0.9123547630046005,
"children": {
"TrainerController._reset_env": {
"total": 3.080981728999973,
"count": 1,
"self": 3.080981728999973
},
"TrainerController.advance": {
"total": 608.9359627679953,
"count": 18201,
"self": 0.45208132199263673,
"children": {
"env_step": {
"total": 608.4838814460027,
"count": 18201,
"self": 473.45127435301356,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.59872016799574,
"count": 18201,
"self": 2.460706945995298,
"children": {
"TorchPolicy.evaluate": {
"total": 132.13801322200044,
"count": 18201,
"self": 132.13801322200044
}
}
},
"workers": {
"total": 0.43388692499337367,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 610.7820291109941,
"count": 18201,
"is_parallel": true,
"self": 282.5590877289892,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007603248999998868,
"count": 1,
"is_parallel": true,
"self": 0.005826285000068765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017769639999301035,
"count": 10,
"is_parallel": true,
"self": 0.0017769639999301035
}
}
},
"UnityEnvironment.step": {
"total": 0.0920879710000122,
"count": 1,
"is_parallel": true,
"self": 0.0007963620000168703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004182430000128079,
"count": 1,
"is_parallel": true,
"self": 0.0004182430000128079
},
"communicator.exchange": {
"total": 0.08861979699997846,
"count": 1,
"is_parallel": true,
"self": 0.08861979699997846
},
"steps_from_proto": {
"total": 0.002253569000004063,
"count": 1,
"is_parallel": true,
"self": 0.00042068800001970885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018328809999843543,
"count": 10,
"is_parallel": true,
"self": 0.0018328809999843543
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 328.22294138200493,
"count": 18200,
"is_parallel": true,
"self": 14.846379214011677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.732821553998406,
"count": 18200,
"is_parallel": true,
"self": 7.732821553998406
},
"communicator.exchange": {
"total": 260.4599934609999,
"count": 18200,
"is_parallel": true,
"self": 260.4599934609999
},
"steps_from_proto": {
"total": 45.183747152994954,
"count": 18200,
"is_parallel": true,
"self": 9.031451009011619,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.152296143983335,
"count": 182000,
"is_parallel": true,
"self": 36.152296143983335
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00023797800008651393,
"count": 1,
"self": 0.00023797800008651393,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 603.3877074949389,
"count": 620152,
"is_parallel": true,
"self": 15.181554102969017,
"children": {
"process_trajectory": {
"total": 329.43346601996984,
"count": 620152,
"is_parallel": true,
"self": 328.60278457496986,
"children": {
"RLTrainer._checkpoint": {
"total": 0.830681444999982,
"count": 4,
"is_parallel": true,
"self": 0.830681444999982
}
}
},
"_update_policy": {
"total": 258.77268737200006,
"count": 90,
"is_parallel": true,
"self": 73.99721390100814,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.77547347099193,
"count": 4584,
"is_parallel": true,
"self": 184.77547347099193
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09896536400003697,
"count": 1,
"self": 0.0011980670000184546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09776729700001852,
"count": 1,
"self": 0.09776729700001852
}
}
}
}
}
}
}