AlexandreManai's picture
First Push
ad1baba verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8241701722145081,
"min": 0.8241701722145081,
"max": 2.8646650314331055,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7887.30859375,
"min": 7887.30859375,
"max": 29368.544921875,
"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": 12.890700340270996,
"min": 0.47481128573417664,
"max": 12.890700340270996,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2513.6865234375,
"min": 92.11338806152344,
"max": 2622.615478515625,
"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": 0.06980487344573667,
"min": 0.06479879644877443,
"max": 0.07654675006607944,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2792194937829467,
"min": 0.2722570186175004,
"max": 0.3636558358626002,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20993501115955557,
"min": 0.13892575181842617,
"max": 0.2892170859610333,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8397400446382223,
"min": 0.5557030072737047,
"max": 1.375996257452404,
"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": 25.636363636363637,
"min": 3.5454545454545454,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 156.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.5454545454545454,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 156.0,
"max": 1388.0,
"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": "1710082272",
"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": "1710082871"
},
"total": 598.6594525669999,
"count": 1,
"self": 0.5932067799999459,
"children": {
"run_training.setup": {
"total": 0.08494903799999065,
"count": 1,
"self": 0.08494903799999065
},
"TrainerController.start_learning": {
"total": 597.981296749,
"count": 1,
"self": 0.8065159760197957,
"children": {
"TrainerController._reset_env": {
"total": 3.872955079999997,
"count": 1,
"self": 3.872955079999997
},
"TrainerController.advance": {
"total": 593.1971123469802,
"count": 18201,
"self": 0.4363330429811185,
"children": {
"env_step": {
"total": 592.7607793039991,
"count": 18201,
"self": 452.5190935239915,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.79336969600433,
"count": 18201,
"self": 2.41791103500384,
"children": {
"TorchPolicy.evaluate": {
"total": 137.3754586610005,
"count": 18201,
"self": 137.3754586610005
}
}
},
"workers": {
"total": 0.44831608400329515,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 596.010785466016,
"count": 18201,
"is_parallel": true,
"self": 277.3078930500128,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00986113600004046,
"count": 1,
"is_parallel": true,
"self": 0.006270419000088623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0035907169999518374,
"count": 10,
"is_parallel": true,
"self": 0.0035907169999518374
}
}
},
"UnityEnvironment.step": {
"total": 0.04985983199992461,
"count": 1,
"is_parallel": true,
"self": 0.001029971999969348,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004654709999840634,
"count": 1,
"is_parallel": true,
"self": 0.0004654709999840634
},
"communicator.exchange": {
"total": 0.04472130199997082,
"count": 1,
"is_parallel": true,
"self": 0.04472130199997082
},
"steps_from_proto": {
"total": 0.003643087000000378,
"count": 1,
"is_parallel": true,
"self": 0.0007919560001710124,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028511309998293655,
"count": 10,
"is_parallel": true,
"self": 0.0028511309998293655
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 318.70289241600324,
"count": 18200,
"is_parallel": true,
"self": 15.599845536007479,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.563977093989479,
"count": 18200,
"is_parallel": true,
"self": 7.563977093989479
},
"communicator.exchange": {
"total": 249.46625479899967,
"count": 18200,
"is_parallel": true,
"self": 249.46625479899967
},
"steps_from_proto": {
"total": 46.07281498700661,
"count": 18200,
"is_parallel": true,
"self": 8.919591018008418,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.15322396899819,
"count": 182000,
"is_parallel": true,
"self": 37.15322396899819
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001942940000390081,
"count": 1,
"self": 0.0001942940000390081,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 585.6076710139434,
"count": 844753,
"is_parallel": true,
"self": 20.64348154591937,
"children": {
"process_trajectory": {
"total": 321.50337812702503,
"count": 844753,
"is_parallel": true,
"self": 320.7448126000253,
"children": {
"RLTrainer._checkpoint": {
"total": 0.758565526999746,
"count": 4,
"is_parallel": true,
"self": 0.758565526999746
}
}
},
"_update_policy": {
"total": 243.46081134099904,
"count": 90,
"is_parallel": true,
"self": 61.27844610099237,
"children": {
"TorchPPOOptimizer.update": {
"total": 182.18236524000667,
"count": 4587,
"is_parallel": true,
"self": 182.18236524000667
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10451905199988687,
"count": 1,
"self": 0.0012873529997250444,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10323169900016183,
"count": 1,
"self": 0.10323169900016183
}
}
}
}
}
}
}