ppo-Huggy-testing / run_logs /timers.json
vicha-w's picture
First try from Huggy tutorial
bd97ec2 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3990658521652222,
"min": 1.3990658521652222,
"max": 1.423021912574768,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70256.890625,
"min": 68608.2734375,
"max": 77370.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.7102615694165,
"min": 88.20892857142857,
"max": 385.4,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49059.0,
"min": 48911.0,
"max": 50167.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999965.0,
"min": 49483.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999965.0,
"min": 49483.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.335113525390625,
"min": 0.03855133801698685,
"max": 2.4424266815185547,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1160.5513916015625,
"min": 4.973122596740723,
"max": 1352.432373046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4823890460329037,
"min": 1.8100821736247041,
"max": 3.9141094812149864,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1730.7473558783531,
"min": 233.50060039758682,
"max": 2147.278117418289,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4823890460329037,
"min": 1.8100821736247041,
"max": 3.9141094812149864,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1730.7473558783531,
"min": 233.50060039758682,
"max": 2147.278117418289,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0169272892109196,
"min": 0.013608630821302843,
"max": 0.019966561473362766,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0338545784218392,
"min": 0.027217261642605687,
"max": 0.05745141104610714,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05305082860092322,
"min": 0.02185297201698025,
"max": 0.06040989477187395,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10610165720184644,
"min": 0.0437059440339605,
"max": 0.17317984451850255,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.493123502324997e-06,
"min": 4.493123502324997e-06,
"max": 0.00029529532656822493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.986247004649995e-06,
"min": 8.986247004649995e-06,
"max": 0.0008436147187951,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10149767499999998,
"min": 0.10149767499999998,
"max": 0.19843177500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20299534999999996,
"min": 0.20299534999999996,
"max": 0.5812049000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.473398249999994e-05,
"min": 8.473398249999994e-05,
"max": 0.0049217455725000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016946796499999988,
"min": 0.00016946796499999988,
"max": 0.01406212451,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709996556",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1709999045"
},
"total": 2489.3012237929997,
"count": 1,
"self": 0.696274196000104,
"children": {
"run_training.setup": {
"total": 0.08359191900001406,
"count": 1,
"self": 0.08359191900001406
},
"TrainerController.start_learning": {
"total": 2488.5213576779997,
"count": 1,
"self": 4.483206335981777,
"children": {
"TrainerController._reset_env": {
"total": 3.044144688000017,
"count": 1,
"self": 3.044144688000017
},
"TrainerController.advance": {
"total": 2480.817698218018,
"count": 231864,
"self": 5.0056525641671215,
"children": {
"env_step": {
"total": 1995.818960174881,
"count": 231864,
"self": 1648.3276544028145,
"children": {
"SubprocessEnvManager._take_step": {
"total": 344.5311303690069,
"count": 231864,
"self": 17.843685955062654,
"children": {
"TorchPolicy.evaluate": {
"total": 326.68744441394426,
"count": 223017,
"self": 326.68744441394426
}
}
},
"workers": {
"total": 2.9601754030596226,
"count": 231864,
"self": 0.0,
"children": {
"worker_root": {
"total": 2480.734035228054,
"count": 231864,
"is_parallel": true,
"self": 1156.6454850650584,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010358279999991282,
"count": 1,
"is_parallel": true,
"self": 0.00027263400005494987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007631939999441784,
"count": 2,
"is_parallel": true,
"self": 0.0007631939999441784
}
}
},
"UnityEnvironment.step": {
"total": 0.030991928999981155,
"count": 1,
"is_parallel": true,
"self": 0.0004067839999493117,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024024399999689194,
"count": 1,
"is_parallel": true,
"self": 0.00024024399999689194
},
"communicator.exchange": {
"total": 0.02954101900002115,
"count": 1,
"is_parallel": true,
"self": 0.02954101900002115
},
"steps_from_proto": {
"total": 0.0008038820000138003,
"count": 1,
"is_parallel": true,
"self": 0.00019834900001569622,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006055329999981041,
"count": 2,
"is_parallel": true,
"self": 0.0006055329999981041
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1324.0885501629955,
"count": 231863,
"is_parallel": true,
"self": 40.53498966903044,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.93553410899568,
"count": 231863,
"is_parallel": true,
"self": 81.93553410899568
},
"communicator.exchange": {
"total": 1109.66815575195,
"count": 231863,
"is_parallel": true,
"self": 1109.66815575195
},
"steps_from_proto": {
"total": 91.94987063301943,
"count": 231863,
"is_parallel": true,
"self": 32.154343650082126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.795526982937304,
"count": 463726,
"is_parallel": true,
"self": 59.795526982937304
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 479.99308547896993,
"count": 231864,
"self": 7.554875206892461,
"children": {
"process_trajectory": {
"total": 153.8858522080791,
"count": 231864,
"self": 152.54962413107876,
"children": {
"RLTrainer._checkpoint": {
"total": 1.336228077000328,
"count": 10,
"self": 1.336228077000328
}
}
},
"_update_policy": {
"total": 318.5523580639984,
"count": 96,
"self": 255.46307583499816,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.08928222900022,
"count": 2880,
"self": 63.08928222900022
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.202000021294225e-06,
"count": 1,
"self": 1.202000021294225e-06
},
"TrainerController._save_models": {
"total": 0.17630723399997805,
"count": 1,
"self": 0.0028576869999596965,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17344954700001836,
"count": 1,
"self": 0.17344954700001836
}
}
}
}
}
}
}