lotek93's picture
first training
d0ca717
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8747074604034424,
"min": 0.8582293391227722,
"max": 2.873250722885132,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8351.70703125,
"min": 8351.70703125,
"max": 29424.9609375,
"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": 11.993210792541504,
"min": 0.24991360306739807,
"max": 11.993210792541504,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2338.676025390625,
"min": 48.483238220214844,
"max": 2411.846923828125,
"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": 0.0654271831671769,
"min": 0.06203128167573025,
"max": 0.07341870830517591,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2617087326687076,
"min": 0.248125126702921,
"max": 0.3670935415258796,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19795358568137766,
"min": 0.13102792230019272,
"max": 0.283193860787387,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7918143427255107,
"min": 0.5241116892007709,
"max": 1.3525204950687932,
"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": 23.84090909090909,
"min": 3.477272727272727,
"max": 23.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1049.0,
"min": 153.0,
"max": 1304.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.84090909090909,
"min": 3.477272727272727,
"max": 23.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1049.0,
"min": 153.0,
"max": 1304.0,
"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": "1674321567",
"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": "1674321995"
},
"total": 428.44730265,
"count": 1,
"self": 0.3841473979998682,
"children": {
"run_training.setup": {
"total": 0.11006127900009233,
"count": 1,
"self": 0.11006127900009233
},
"TrainerController.start_learning": {
"total": 427.953093973,
"count": 1,
"self": 0.5768155140056024,
"children": {
"TrainerController._reset_env": {
"total": 9.53045462,
"count": 1,
"self": 9.53045462
},
"TrainerController.advance": {
"total": 417.7373847369943,
"count": 18199,
"self": 0.27690726098569485,
"children": {
"env_step": {
"total": 417.4604774760086,
"count": 18199,
"self": 276.5045436540131,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.67154268099296,
"count": 18199,
"self": 1.3900174250119335,
"children": {
"TorchPolicy.evaluate": {
"total": 139.28152525598102,
"count": 18199,
"self": 32.504557744991416,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.7769675109896,
"count": 18199,
"self": 106.7769675109896
}
}
}
}
},
"workers": {
"total": 0.2843911410025157,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.66573628298147,
"count": 18199,
"is_parallel": true,
"self": 202.1766986479572,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006603106000056869,
"count": 1,
"is_parallel": true,
"self": 0.004265346000238424,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002337759999818445,
"count": 10,
"is_parallel": true,
"self": 0.002337759999818445
}
}
},
"UnityEnvironment.step": {
"total": 0.041759363999972265,
"count": 1,
"is_parallel": true,
"self": 0.0004757059999747071,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037181300001520867,
"count": 1,
"is_parallel": true,
"self": 0.00037181300001520867
},
"communicator.exchange": {
"total": 0.039169606999962525,
"count": 1,
"is_parallel": true,
"self": 0.039169606999962525
},
"steps_from_proto": {
"total": 0.0017422380000198245,
"count": 1,
"is_parallel": true,
"self": 0.0003967130001001351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013455249999196894,
"count": 10,
"is_parallel": true,
"self": 0.0013455249999196894
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.48903763502426,
"count": 18198,
"is_parallel": true,
"self": 8.306370326034994,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.885065307993159,
"count": 18198,
"is_parallel": true,
"self": 4.885065307993159
},
"communicator.exchange": {
"total": 179.14129415699995,
"count": 18198,
"is_parallel": true,
"self": 179.14129415699995
},
"steps_from_proto": {
"total": 32.15630784399616,
"count": 18198,
"is_parallel": true,
"self": 6.70771326304498,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.44859458095118,
"count": 181980,
"is_parallel": true,
"self": 25.44859458095118
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.8140999979295884e-05,
"count": 1,
"self": 4.8140999979295884e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 414.9922953069149,
"count": 345559,
"is_parallel": true,
"self": 8.7091626529093,
"children": {
"process_trajectory": {
"total": 238.72815792700635,
"count": 345559,
"is_parallel": true,
"self": 238.05625268700646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6719052399998873,
"count": 4,
"is_parallel": true,
"self": 0.6719052399998873
}
}
},
"_update_policy": {
"total": 167.55497472699926,
"count": 90,
"is_parallel": true,
"self": 42.655423665998455,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.8995510610008,
"count": 4587,
"is_parallel": true,
"self": 124.8995510610008
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10839096100016832,
"count": 1,
"self": 0.0007819270001618861,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10760903400000643,
"count": 1,
"self": 0.10760903400000643
}
}
}
}
}
}
}