happyrabbit's picture
First training of SnowballTarget
61a23ff
raw
history blame contribute delete
No virus
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.045030117034912,
"min": 1.045030117034912,
"max": 2.866621255874634,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9989.443359375,
"min": 9989.443359375,
"max": 29357.068359375,
"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": 12.725601196289062,
"min": 0.44608911871910095,
"max": 12.725601196289062,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2481.4921875,
"min": 86.54129028320312,
"max": 2583.603759765625,
"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": 0.06525121480894193,
"min": 0.06425503801680559,
"max": 0.07612256456595073,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2610048592357677,
"min": 0.25702015206722234,
"max": 0.37098531560817116,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20785879358357073,
"min": 0.11722981360257037,
"max": 0.2820732818514693,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8314351743342829,
"min": 0.4689192544102815,
"max": 1.3976522374386882,
"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": 24.795454545454547,
"min": 3.522727272727273,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1091.0,
"min": 155.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.795454545454547,
"min": 3.522727272727273,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1091.0,
"min": 155.0,
"max": 1368.0,
"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": "1679054486",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679054973"
},
"total": 487.14242250300003,
"count": 1,
"self": 0.38444758300011017,
"children": {
"run_training.setup": {
"total": 0.10368657999993047,
"count": 1,
"self": 0.10368657999993047
},
"TrainerController.start_learning": {
"total": 486.65428834,
"count": 1,
"self": 0.5557708039955287,
"children": {
"TrainerController._reset_env": {
"total": 10.00106814500009,
"count": 1,
"self": 10.00106814500009
},
"TrainerController.advance": {
"total": 475.9577296450045,
"count": 18202,
"self": 0.2786597150002308,
"children": {
"env_step": {
"total": 475.6790699300043,
"count": 18202,
"self": 342.6465898730289,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.74268091998238,
"count": 18202,
"self": 1.7650155059793633,
"children": {
"TorchPolicy.evaluate": {
"total": 130.977665414003,
"count": 18202,
"self": 130.977665414003
}
}
},
"workers": {
"total": 0.28979913699299686,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 485.0703599599917,
"count": 18202,
"is_parallel": true,
"self": 234.58418791199256,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006119834999935847,
"count": 1,
"is_parallel": true,
"self": 0.004425435999564797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016943990003710496,
"count": 10,
"is_parallel": true,
"self": 0.0016943990003710496
}
}
},
"UnityEnvironment.step": {
"total": 0.04335534599999846,
"count": 1,
"is_parallel": true,
"self": 0.0005909959998007253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004427020001003257,
"count": 1,
"is_parallel": true,
"self": 0.0004427020001003257
},
"communicator.exchange": {
"total": 0.04021678000003703,
"count": 1,
"is_parallel": true,
"self": 0.04021678000003703
},
"steps_from_proto": {
"total": 0.002104868000060378,
"count": 1,
"is_parallel": true,
"self": 0.0005368359995827632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001568032000477615,
"count": 10,
"is_parallel": true,
"self": 0.001568032000477615
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.48617204799916,
"count": 18201,
"is_parallel": true,
"self": 9.992527509011097,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.649774439992598,
"count": 18201,
"is_parallel": true,
"self": 5.649774439992598
},
"communicator.exchange": {
"total": 201.10753972699308,
"count": 18201,
"is_parallel": true,
"self": 201.10753972699308
},
"steps_from_proto": {
"total": 33.736330372002385,
"count": 18201,
"is_parallel": true,
"self": 6.813846399030808,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.922483972971577,
"count": 182010,
"is_parallel": true,
"self": 26.922483972971577
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015107699982763734,
"count": 1,
"self": 0.00015107699982763734,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 472.24046371405075,
"count": 412634,
"is_parallel": true,
"self": 10.874647177094857,
"children": {
"process_trajectory": {
"total": 262.4289418579549,
"count": 412634,
"is_parallel": true,
"self": 260.8696756479551,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5592662099998051,
"count": 4,
"is_parallel": true,
"self": 1.5592662099998051
}
}
},
"_update_policy": {
"total": 198.936874679001,
"count": 90,
"is_parallel": true,
"self": 72.86402239899598,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.07285228000501,
"count": 4587,
"is_parallel": true,
"self": 126.07285228000501
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1395686690000275,
"count": 1,
"self": 0.0008639860000130284,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13870468300001448,
"count": 1,
"self": 0.13870468300001448
}
}
}
}
}
}
}