jinghuanHuggingface's picture
First Push
0e2549f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9688221216201782,
"min": 0.9688221216201782,
"max": 2.877946376800537,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9250.3134765625,
"min": 9250.3134765625,
"max": 29504.70703125,
"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": 12.813727378845215,
"min": 0.336683988571167,
"max": 12.813727378845215,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2498.6767578125,
"min": 65.31669616699219,
"max": 2568.88232421875,
"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": 0.06590771171260498,
"min": 0.06357329362574235,
"max": 0.07493227796180243,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26363084685041993,
"min": 0.26363084685041993,
"max": 0.3535302949552287,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20092715680891393,
"min": 0.1150091671996622,
"max": 0.30185134854971196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8037086272356557,
"min": 0.4600366687986488,
"max": 1.50925674274856,
"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": 25.522727272727273,
"min": 3.159090909090909,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1123.0,
"min": 139.0,
"max": 1367.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.522727272727273,
"min": 3.159090909090909,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1123.0,
"min": 139.0,
"max": 1367.0,
"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": "1711033991",
"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": "1711034435"
},
"total": 443.690388452,
"count": 1,
"self": 0.4353858439999385,
"children": {
"run_training.setup": {
"total": 0.05498476299999311,
"count": 1,
"self": 0.05498476299999311
},
"TrainerController.start_learning": {
"total": 443.20001784500005,
"count": 1,
"self": 0.5625761919919796,
"children": {
"TrainerController._reset_env": {
"total": 3.031401497000047,
"count": 1,
"self": 3.031401497000047
},
"TrainerController.advance": {
"total": 439.51622776200816,
"count": 18198,
"self": 0.26479512299499675,
"children": {
"env_step": {
"total": 439.25143263901316,
"count": 18198,
"self": 280.5122484449905,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.46238598702257,
"count": 18198,
"self": 1.4411126980309064,
"children": {
"TorchPolicy.evaluate": {
"total": 157.02127328899167,
"count": 18198,
"self": 157.02127328899167
}
}
},
"workers": {
"total": 0.27679820700006985,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.029574499997,
"count": 18198,
"is_parallel": true,
"self": 223.8894760370074,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005956029000003582,
"count": 1,
"is_parallel": true,
"self": 0.004410719000134122,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015453099998694597,
"count": 10,
"is_parallel": true,
"self": 0.0015453099998694597
}
}
},
"UnityEnvironment.step": {
"total": 0.07206581499997355,
"count": 1,
"is_parallel": true,
"self": 0.0006774129999485012,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039765500002886256,
"count": 1,
"is_parallel": true,
"self": 0.00039765500002886256
},
"communicator.exchange": {
"total": 0.06875487800004976,
"count": 1,
"is_parallel": true,
"self": 0.06875487800004976
},
"steps_from_proto": {
"total": 0.002235868999946433,
"count": 1,
"is_parallel": true,
"self": 0.0005177530001674313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017181159997790019,
"count": 10,
"is_parallel": true,
"self": 0.0017181159997790019
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.1400984629896,
"count": 18197,
"is_parallel": true,
"self": 10.098323826962542,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.288899722006477,
"count": 18197,
"is_parallel": true,
"self": 5.288899722006477
},
"communicator.exchange": {
"total": 169.20038211099904,
"count": 18197,
"is_parallel": true,
"self": 169.20038211099904
},
"steps_from_proto": {
"total": 33.55249280302155,
"count": 18197,
"is_parallel": true,
"self": 6.211431381024795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.341061421996756,
"count": 181970,
"is_parallel": true,
"self": 27.341061421996756
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001279699999940931,
"count": 1,
"self": 0.0001279699999940931,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 433.69420240897614,
"count": 684579,
"is_parallel": true,
"self": 15.223666940075304,
"children": {
"process_trajectory": {
"total": 239.8177510309016,
"count": 684579,
"is_parallel": true,
"self": 239.01067881490167,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8070722159999377,
"count": 4,
"is_parallel": true,
"self": 0.8070722159999377
}
}
},
"_update_policy": {
"total": 178.65278443799923,
"count": 90,
"is_parallel": true,
"self": 49.51171764499691,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.14106679300232,
"count": 4587,
"is_parallel": true,
"self": 129.14106679300232
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08968442399986998,
"count": 1,
"self": 0.0010670229999050207,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08861740099996496,
"count": 1,
"self": 0.08861740099996496
}
}
}
}
}
}
}