panos-span's picture
First Push
a5dc2fd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9801486134529114,
"min": 0.9801486134529114,
"max": 2.869128704071045,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9358.458984375,
"min": 9358.458984375,
"max": 29414.30859375,
"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": 12.555831909179688,
"min": 0.37945738434791565,
"max": 12.555831909179688,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2448.38720703125,
"min": 73.61473083496094,
"max": 2546.9287109375,
"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": 0.067491833148333,
"min": 0.06195888565714852,
"max": 0.07310721769274951,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.269967332593332,
"min": 0.24783554262859409,
"max": 0.3615037497535619,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21828369051218033,
"min": 0.11160720024125506,
"max": 0.266897260120102,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8731347620487213,
"min": 0.44642880096502024,
"max": 1.3094552591735242,
"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": 24.65909090909091,
"min": 3.3636363636363638,
"max": 24.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1085.0,
"min": 148.0,
"max": 1361.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.65909090909091,
"min": 3.3636363636363638,
"max": 24.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1085.0,
"min": 148.0,
"max": 1361.0,
"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": "1709825651",
"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": "1709826077"
},
"total": 426.228809663,
"count": 1,
"self": 0.49411241699999664,
"children": {
"run_training.setup": {
"total": 0.05369949500004623,
"count": 1,
"self": 0.05369949500004623
},
"TrainerController.start_learning": {
"total": 425.68099775099995,
"count": 1,
"self": 0.5144149500055164,
"children": {
"TrainerController._reset_env": {
"total": 3.235948060999931,
"count": 1,
"self": 3.235948060999931
},
"TrainerController.advance": {
"total": 421.8404718839947,
"count": 18199,
"self": 0.24897460099577984,
"children": {
"env_step": {
"total": 421.59149728299894,
"count": 18199,
"self": 269.6437977060044,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.68717932899392,
"count": 18199,
"self": 1.6437956819966075,
"children": {
"TorchPolicy.evaluate": {
"total": 150.0433836469973,
"count": 18199,
"self": 150.0433836469973
}
}
},
"workers": {
"total": 0.2605202480006028,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.60565011300446,
"count": 18199,
"is_parallel": true,
"self": 215.7117604329958,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007648933000041325,
"count": 1,
"is_parallel": true,
"self": 0.006140235000088978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015086979999523464,
"count": 10,
"is_parallel": true,
"self": 0.0015086979999523464
}
}
},
"UnityEnvironment.step": {
"total": 0.03586718900010055,
"count": 1,
"is_parallel": true,
"self": 0.0006881390000899046,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039814000001570093,
"count": 1,
"is_parallel": true,
"self": 0.00039814000001570093
},
"communicator.exchange": {
"total": 0.03281472900005156,
"count": 1,
"is_parallel": true,
"self": 0.03281472900005156
},
"steps_from_proto": {
"total": 0.00196618099994339,
"count": 1,
"is_parallel": true,
"self": 0.00039404499989359465,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015721360000497953,
"count": 10,
"is_parallel": true,
"self": 0.0015721360000497953
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.89388968000867,
"count": 18198,
"is_parallel": true,
"self": 9.900821563998193,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.162200982022682,
"count": 18198,
"is_parallel": true,
"self": 5.162200982022682
},
"communicator.exchange": {
"total": 161.83892637098256,
"count": 18198,
"is_parallel": true,
"self": 161.83892637098256
},
"steps_from_proto": {
"total": 31.991940763005232,
"count": 18198,
"is_parallel": true,
"self": 5.90527878800151,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.08666197500372,
"count": 181980,
"is_parallel": true,
"self": 26.08666197500372
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014521999992211931,
"count": 1,
"self": 0.00014521999992211931,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 416.43049821609077,
"count": 649538,
"is_parallel": true,
"self": 14.063154648056866,
"children": {
"process_trajectory": {
"total": 229.52076717903333,
"count": 649538,
"is_parallel": true,
"self": 229.02466957103366,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4960976079996726,
"count": 4,
"is_parallel": true,
"self": 0.4960976079996726
}
}
},
"_update_policy": {
"total": 172.84657638900057,
"count": 90,
"is_parallel": true,
"self": 50.55599887199935,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.29057751700122,
"count": 4587,
"is_parallel": true,
"self": 122.29057751700122
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0900176359998568,
"count": 1,
"self": 0.0009993789997224667,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08901825700013433,
"count": 1,
"self": 0.08901825700013433
}
}
}
}
}
}
}