pyflynn's picture
resnet-ppo for SnowballTarget
5caa8af
raw
history blame contribute delete
No virus
19 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9627605676651001,
"min": 0.9627605676651001,
"max": 2.8760147094726562,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9181.84765625,
"min": 9181.84765625,
"max": 29453.265625,
"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": 12.84013557434082,
"min": 0.37715378403663635,
"max": 12.902356147766113,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2503.826416015625,
"min": 73.16783142089844,
"max": 2632.08056640625,
"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": 0.06502339295933351,
"min": 0.061372166166798775,
"max": 0.07587366399529856,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26009357183733406,
"min": 0.2454886646671951,
"max": 0.3793683199764928,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2034858539700508,
"min": 0.13180513837027782,
"max": 0.30716886397670295,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8139434158802032,
"min": 0.5272205534811113,
"max": 1.5358443198835148,
"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": 24.59090909090909,
"min": 3.590909090909091,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1082.0,
"min": 158.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.59090909090909,
"min": 3.590909090909091,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1082.0,
"min": 158.0,
"max": 1409.0,
"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": "1677077629",
"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=SnowballTarget2 --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": "1677078104"
},
"total": 474.68241496300004,
"count": 1,
"self": 0.42953667900007986,
"children": {
"run_training.setup": {
"total": 0.11277407199997924,
"count": 1,
"self": 0.11277407199997924
},
"TrainerController.start_learning": {
"total": 474.140104212,
"count": 1,
"self": 0.5620967189693147,
"children": {
"TrainerController._reset_env": {
"total": 11.488993687000061,
"count": 1,
"self": 11.488993687000061
},
"TrainerController.advance": {
"total": 461.9540859290307,
"count": 18202,
"self": 0.2733529870123448,
"children": {
"env_step": {
"total": 461.6807329420184,
"count": 18202,
"self": 319.02069828801723,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.3901217529998,
"count": 18202,
"self": 1.467447878986377,
"children": {
"TorchPolicy.evaluate": {
"total": 140.9226738740134,
"count": 18202,
"self": 31.853262655010894,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.06941121900252,
"count": 18202,
"self": 109.06941121900252
}
}
}
}
},
"workers": {
"total": 0.2699129010013621,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.7081361610101,
"count": 18202,
"is_parallel": true,
"self": 234.32320092100156,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006162587999938296,
"count": 1,
"is_parallel": true,
"self": 0.0038567870000179028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023058009999203932,
"count": 10,
"is_parallel": true,
"self": 0.0023058009999203932
}
}
},
"UnityEnvironment.step": {
"total": 0.0429484499999262,
"count": 1,
"is_parallel": true,
"self": 0.0006027479998920171,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002915300000267962,
"count": 1,
"is_parallel": true,
"self": 0.0002915300000267962
},
"communicator.exchange": {
"total": 0.0400499890000674,
"count": 1,
"is_parallel": true,
"self": 0.0400499890000674
},
"steps_from_proto": {
"total": 0.002004182999939985,
"count": 1,
"is_parallel": true,
"self": 0.00043899999980112625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001565183000138859,
"count": 10,
"is_parallel": true,
"self": 0.001565183000138859
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.38493524000853,
"count": 18201,
"is_parallel": true,
"self": 9.687356245004935,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2267340660005175,
"count": 18201,
"is_parallel": true,
"self": 5.2267340660005175
},
"communicator.exchange": {
"total": 191.93477821699219,
"count": 18201,
"is_parallel": true,
"self": 191.93477821699219
},
"steps_from_proto": {
"total": 31.536066712010893,
"count": 18201,
"is_parallel": true,
"self": 6.714250155030754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.82181655698014,
"count": 182010,
"is_parallel": true,
"self": 24.82181655698014
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014303800003290235,
"count": 1,
"self": 0.00014303800003290235,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.6909745550165,
"count": 394161,
"is_parallel": true,
"self": 9.954992526984142,
"children": {
"process_trajectory": {
"total": 260.1367116470317,
"count": 394161,
"is_parallel": true,
"self": 259.02678479603196,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1099268509997273,
"count": 4,
"is_parallel": true,
"self": 1.1099268509997273
}
}
},
"_update_policy": {
"total": 188.59927038100068,
"count": 90,
"is_parallel": true,
"self": 63.892759858003615,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.70651052299706,
"count": 4587,
"is_parallel": true,
"self": 124.70651052299706
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13478483899984894,
"count": 1,
"self": 0.0011800449999554985,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13360479399989345,
"count": 1,
"self": 0.13360479399989345
}
}
}
}
}
}
}