Your-Cheese's picture
Snowball Target with PPO
c98d5f3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0782997608184814,
"min": 1.0782997608184814,
"max": 2.8590848445892334,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10295.6064453125,
"min": 10295.6064453125,
"max": 29279.88671875,
"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": 12.571306228637695,
"min": 0.29027196764945984,
"max": 12.571306228637695,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2451.40478515625,
"min": 56.31275939941406,
"max": 2526.4462890625,
"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": 0.06887668720774659,
"min": 0.061368231046613875,
"max": 0.074403152040231,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27550674883098636,
"min": 0.2669868179809247,
"max": 0.372015760201155,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20692944190665788,
"min": 0.11406990963687169,
"max": 0.27674784122728835,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8277177676266315,
"min": 0.45627963854748677,
"max": 1.3837392061364417,
"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": 25.318181818181817,
"min": 3.25,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 143.0,
"max": 1362.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.25,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 143.0,
"max": 1362.0,
"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": "1677045516",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1677045980"
},
"total": 464.07444549600007,
"count": 1,
"self": 0.4410700070000644,
"children": {
"run_training.setup": {
"total": 0.11129906899998332,
"count": 1,
"self": 0.11129906899998332
},
"TrainerController.start_learning": {
"total": 463.52207642,
"count": 1,
"self": 0.5659563200035223,
"children": {
"TrainerController._reset_env": {
"total": 9.93576927800001,
"count": 1,
"self": 9.93576927800001
},
"TrainerController.advance": {
"total": 452.8897262149964,
"count": 18201,
"self": 0.28182189600431684,
"children": {
"env_step": {
"total": 452.6079043189921,
"count": 18201,
"self": 312.98112861798904,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.3482314249997,
"count": 18201,
"self": 1.604184870004019,
"children": {
"TorchPolicy.evaluate": {
"total": 137.7440465549957,
"count": 18201,
"self": 30.970993661998193,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.7730528929975,
"count": 18201,
"self": 106.7730528929975
}
}
}
}
},
"workers": {
"total": 0.27854427600334475,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.0380575810084,
"count": 18201,
"is_parallel": true,
"self": 224.1022491170147,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007601146000013159,
"count": 1,
"is_parallel": true,
"self": 0.0033040670001014405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004297078999911719,
"count": 10,
"is_parallel": true,
"self": 0.004297078999911719
}
}
},
"UnityEnvironment.step": {
"total": 0.06730969599999526,
"count": 1,
"is_parallel": true,
"self": 0.0005359200000043529,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004526079999891408,
"count": 1,
"is_parallel": true,
"self": 0.0004526079999891408
},
"communicator.exchange": {
"total": 0.062337065999997776,
"count": 1,
"is_parallel": true,
"self": 0.062337065999997776
},
"steps_from_proto": {
"total": 0.003984102000003986,
"count": 1,
"is_parallel": true,
"self": 0.0004349740000293423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003549127999974644,
"count": 10,
"is_parallel": true,
"self": 0.003549127999974644
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.93580846399368,
"count": 18200,
"is_parallel": true,
"self": 9.478243108998925,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.139733239997042,
"count": 18200,
"is_parallel": true,
"self": 5.139733239997042
},
"communicator.exchange": {
"total": 192.08859590199626,
"count": 18200,
"is_parallel": true,
"self": 192.08859590199626
},
"steps_from_proto": {
"total": 31.229236213001457,
"count": 18200,
"is_parallel": true,
"self": 6.810853655990627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.41838255701083,
"count": 182000,
"is_parallel": true,
"self": 24.41838255701083
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014255300004606397,
"count": 1,
"self": 0.00014255300004606397,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 449.6545876039941,
"count": 406276,
"is_parallel": true,
"self": 10.111621364995528,
"children": {
"process_trajectory": {
"total": 255.87774947699762,
"count": 406276,
"is_parallel": true,
"self": 255.15712289999777,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7206265769998481,
"count": 4,
"is_parallel": true,
"self": 0.7206265769998481
}
}
},
"_update_policy": {
"total": 183.66521676200097,
"count": 90,
"is_parallel": true,
"self": 64.80328261000125,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.86193415199972,
"count": 4587,
"is_parallel": true,
"self": 118.86193415199972
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13048205400002644,
"count": 1,
"self": 0.0009649060000356258,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1295171479999908,
"count": 1,
"self": 0.1295171479999908
}
}
}
}
}
}
}