chist's picture
First Push
e936f67
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9370207190513611,
"min": 0.9370207190513611,
"max": 2.8630192279815674,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8946.673828125,
"min": 8946.673828125,
"max": 29320.1796875,
"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": 12.882400512695312,
"min": 0.38817542791366577,
"max": 12.882400512695312,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2512.068115234375,
"min": 75.3060302734375,
"max": 2618.1708984375,
"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": 0.06877355136937552,
"min": 0.06412401485385821,
"max": 0.0730867486569503,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2750942054775021,
"min": 0.25941292708254576,
"max": 0.36543374328475153,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17215784536857232,
"min": 0.11050157371894731,
"max": 0.2813310198339761,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6886313814742893,
"min": 0.44200629487578924,
"max": 1.4066550991698807,
"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": 3.2045454545454546,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1091.0,
"min": 141.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.795454545454547,
"min": 3.2045454545454546,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1091.0,
"min": 141.0,
"max": 1407.0,
"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": "1673542360",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673542845"
},
"total": 485.684448992,
"count": 1,
"self": 0.4124022859999741,
"children": {
"run_training.setup": {
"total": 0.1184109569999805,
"count": 1,
"self": 0.1184109569999805
},
"TrainerController.start_learning": {
"total": 485.15363574900005,
"count": 1,
"self": 0.6554489119984055,
"children": {
"TrainerController._reset_env": {
"total": 6.848220844999986,
"count": 1,
"self": 6.848220844999986
},
"TrainerController.advance": {
"total": 477.5163909860016,
"count": 18200,
"self": 0.36425952199908807,
"children": {
"env_step": {
"total": 477.15213146400254,
"count": 18200,
"self": 314.29647313399937,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.50444141299985,
"count": 18200,
"self": 1.6531936389926614,
"children": {
"TorchPolicy.evaluate": {
"total": 160.8512477740072,
"count": 18200,
"self": 36.62092068601066,
"children": {
"TorchPolicy.sample_actions": {
"total": 124.23032708799653,
"count": 18200,
"self": 124.23032708799653
}
}
}
}
},
"workers": {
"total": 0.35121691700328483,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 483.5607118280006,
"count": 18200,
"is_parallel": true,
"self": 227.93613187699606,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006013012000011031,
"count": 1,
"is_parallel": true,
"self": 0.0035657850000347935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024472269999762375,
"count": 10,
"is_parallel": true,
"self": 0.0024472269999762375
}
}
},
"UnityEnvironment.step": {
"total": 0.03658315900000275,
"count": 1,
"is_parallel": true,
"self": 0.0005628250000029311,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003622929999949065,
"count": 1,
"is_parallel": true,
"self": 0.0003622929999949065
},
"communicator.exchange": {
"total": 0.03355575000000499,
"count": 1,
"is_parallel": true,
"self": 0.03355575000000499
},
"steps_from_proto": {
"total": 0.002102290999999923,
"count": 1,
"is_parallel": true,
"self": 0.00046915299995475834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016331380000451645,
"count": 10,
"is_parallel": true,
"self": 0.0016331380000451645
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.62457995100453,
"count": 18199,
"is_parallel": true,
"self": 9.607657358003394,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.811322557001745,
"count": 18199,
"is_parallel": true,
"self": 5.811322557001745
},
"communicator.exchange": {
"total": 204.4590180799981,
"count": 18199,
"is_parallel": true,
"self": 204.4590180799981
},
"steps_from_proto": {
"total": 35.74658195600131,
"count": 18199,
"is_parallel": true,
"self": 8.126648020019445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.619933935981862,
"count": 181990,
"is_parallel": true,
"self": 27.619933935981862
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.9728999922772346e-05,
"count": 1,
"self": 3.9728999922772346e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 474.06962586501,
"count": 397066,
"is_parallel": true,
"self": 10.631930454025337,
"children": {
"process_trajectory": {
"total": 273.66608060298506,
"count": 397066,
"is_parallel": true,
"self": 272.8748722659849,
"children": {
"RLTrainer._checkpoint": {
"total": 0.791208337000171,
"count": 4,
"is_parallel": true,
"self": 0.791208337000171
}
}
},
"_update_policy": {
"total": 189.77161480799958,
"count": 90,
"is_parallel": true,
"self": 45.231696775000955,
"children": {
"TorchPPOOptimizer.update": {
"total": 144.53991803299863,
"count": 4587,
"is_parallel": true,
"self": 144.53991803299863
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13353527700007817,
"count": 1,
"self": 0.0010185530001081133,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13251672399997005,
"count": 1,
"self": 0.13251672399997005
}
}
}
}
}
}
}