ethan-lam's picture
First Push
3d6a76a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8522173762321472,
"min": 0.8522173762321472,
"max": 2.861510753631592,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8136.9716796875,
"min": 8136.9716796875,
"max": 29304.73046875,
"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": 12.805288314819336,
"min": 0.3606387972831726,
"max": 12.841880798339844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2497.03125,
"min": 69.96392822265625,
"max": 2619.74365234375,
"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": 0.06836823753219594,
"min": 0.061737779264826806,
"max": 0.07592962056821538,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27347295012878375,
"min": 0.24695111705930722,
"max": 0.36002004899337947,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2017640378691402,
"min": 0.11696952892987825,
"max": 0.30022643044883124,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8070561514765608,
"min": 0.467878115719513,
"max": 1.5011321522441563,
"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": 25.09090909090909,
"min": 3.340909090909091,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 147.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 3.340909090909091,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 147.0,
"max": 1384.0,
"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": "1712549275",
"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": "1712549720"
},
"total": 444.283943045,
"count": 1,
"self": 0.44117120500004603,
"children": {
"run_training.setup": {
"total": 0.06096366599990688,
"count": 1,
"self": 0.06096366599990688
},
"TrainerController.start_learning": {
"total": 443.78180817400005,
"count": 1,
"self": 0.554342930004168,
"children": {
"TrainerController._reset_env": {
"total": 2.9483812830000034,
"count": 1,
"self": 2.9483812830000034
},
"TrainerController.advance": {
"total": 440.185253516996,
"count": 18199,
"self": 0.25487875699093365,
"children": {
"env_step": {
"total": 439.93037476000507,
"count": 18199,
"self": 282.0180374040083,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.6249371549942,
"count": 18199,
"self": 1.4550484039824596,
"children": {
"TorchPolicy.evaluate": {
"total": 156.16988875101174,
"count": 18199,
"self": 156.16988875101174
}
}
},
"workers": {
"total": 0.28740020100258334,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.70347117700396,
"count": 18199,
"is_parallel": true,
"self": 221.81374382298634,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005734643999971922,
"count": 1,
"is_parallel": true,
"self": 0.004135306999955901,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015993370000160212,
"count": 10,
"is_parallel": true,
"self": 0.0015993370000160212
}
}
},
"UnityEnvironment.step": {
"total": 0.03579891699996551,
"count": 1,
"is_parallel": true,
"self": 0.0006900469999209236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004137409999884767,
"count": 1,
"is_parallel": true,
"self": 0.0004137409999884767
},
"communicator.exchange": {
"total": 0.032738881999989644,
"count": 1,
"is_parallel": true,
"self": 0.032738881999989644
},
"steps_from_proto": {
"total": 0.001956247000066469,
"count": 1,
"is_parallel": true,
"self": 0.00038013400001091213,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015761130000555568,
"count": 10,
"is_parallel": true,
"self": 0.0015761130000555568
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 220.88972735401762,
"count": 18198,
"is_parallel": true,
"self": 10.282560398004989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.415555435996339,
"count": 18198,
"is_parallel": true,
"self": 5.415555435996339
},
"communicator.exchange": {
"total": 171.98457603900795,
"count": 18198,
"is_parallel": true,
"self": 171.98457603900795
},
"steps_from_proto": {
"total": 33.20703548100835,
"count": 18198,
"is_parallel": true,
"self": 6.225011674037205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.982023806971142,
"count": 181980,
"is_parallel": true,
"self": 26.982023806971142
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015702099994996388,
"count": 1,
"self": 0.00015702099994996388,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.6302640620286,
"count": 684200,
"is_parallel": true,
"self": 14.302544070054978,
"children": {
"process_trajectory": {
"total": 239.39454290997435,
"count": 684200,
"is_parallel": true,
"self": 238.8492675869744,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5452753229999416,
"count": 4,
"is_parallel": true,
"self": 0.5452753229999416
}
}
},
"_update_policy": {
"total": 180.93317708199925,
"count": 90,
"is_parallel": true,
"self": 51.39612833999604,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.5370487420032,
"count": 4587,
"is_parallel": true,
"self": 129.5370487420032
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09367342299992742,
"count": 1,
"self": 0.0010622669997246703,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09261115600020275,
"count": 1,
"self": 0.09261115600020275
}
}
}
}
}
}
}