ppo-Huggy / run_logs /timers.json
lectura's picture
Huggy
3ae010d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4058396816253662,
"min": 1.4058396816253662,
"max": 1.4261128902435303,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69136.3828125,
"min": 22665.83984375,
"max": 73330.015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.74364406779661,
"min": 83.13973063973064,
"max": 379.6666666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49439.0,
"min": 11825.0,
"max": 50116.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49693.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49693.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3627758026123047,
"min": -0.015249422751367092,
"max": 2.4570391178131104,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1115.230224609375,
"min": -0.5184803605079651,
"max": 1434.489990234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6445536910224767,
"min": 1.5816080675405615,
"max": 4.046008704839199,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1720.229342162609,
"min": 53.77467429637909,
"max": 2311.678420126438,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6445536910224767,
"min": 1.5816080675405615,
"max": 4.046008704839199,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1720.229342162609,
"min": 53.77467429637909,
"max": 2311.678420126438,
"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
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015872381889696245,
"min": 0.012998376017276315,
"max": 0.019609105717002723,
"count": 39
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047617145669088735,
"min": 0.02599675203455263,
"max": 0.05738897766835483,
"count": 39
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04335055814849006,
"min": 0.024900605570938854,
"max": 0.06460842993110419,
"count": 39
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13005167444547017,
"min": 0.05480164407442013,
"max": 0.17618628591299057,
"count": 39
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.749648750150012e-06,
"min": 3.749648750150012e-06,
"max": 0.0002895659284780249,
"count": 39
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1248946250450037e-05,
"min": 1.1248946250450037e-05,
"max": 0.00084558046813985,
"count": 39
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124985000000002,
"min": 0.10124985000000002,
"max": 0.19652197500000002,
"count": 39
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30374955000000003,
"min": 0.20771444999999994,
"max": 0.58186015,
"count": 39
},
"Huggy.Policy.Beta.mean": {
"value": 7.236751500000023e-05,
"min": 7.236751500000023e-05,
"max": 0.0048264465525000005,
"count": 39
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021710254500000066,
"min": 0.00021710254500000066,
"max": 0.014094821484999999,
"count": 39
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1701414337",
"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=Huggy --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701416752"
},
"total": 2414.821471321,
"count": 1,
"self": 0.49034239600041474,
"children": {
"run_training.setup": {
"total": 0.0859794600000896,
"count": 1,
"self": 0.0859794600000896
},
"TrainerController.start_learning": {
"total": 2414.2451494649995,
"count": 1,
"self": 4.604668412245701,
"children": {
"TrainerController._reset_env": {
"total": 3.504449845999943,
"count": 1,
"self": 3.504449845999943
},
"TrainerController.advance": {
"total": 2406.025277328754,
"count": 227666,
"self": 4.645238614699338,
"children": {
"env_step": {
"total": 1901.4923164660133,
"count": 227666,
"self": 1574.2414089120898,
"children": {
"SubprocessEnvManager._take_step": {
"total": 324.35369889694493,
"count": 227666,
"self": 16.751475642908417,
"children": {
"TorchPolicy.evaluate": {
"total": 307.6022232540365,
"count": 218805,
"self": 307.6022232540365
}
}
},
"workers": {
"total": 2.8972086569785915,
"count": 227666,
"self": 0.0,
"children": {
"worker_root": {
"total": 2406.860999964033,
"count": 227666,
"is_parallel": true,
"self": 1129.1029825081062,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009592760000032285,
"count": 1,
"is_parallel": true,
"self": 0.0002986870001677744,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006605889998354542,
"count": 2,
"is_parallel": true,
"self": 0.0006605889998354542
}
}
},
"UnityEnvironment.step": {
"total": 0.030444048999925144,
"count": 1,
"is_parallel": true,
"self": 0.00031487699970966787,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002277070000218373,
"count": 1,
"is_parallel": true,
"self": 0.0002277070000218373
},
"communicator.exchange": {
"total": 0.02920692200018493,
"count": 1,
"is_parallel": true,
"self": 0.02920692200018493
},
"steps_from_proto": {
"total": 0.0006945430000087072,
"count": 1,
"is_parallel": true,
"self": 0.0001805780000267987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005139649999819085,
"count": 2,
"is_parallel": true,
"self": 0.0005139649999819085
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1277.7580174559268,
"count": 227665,
"is_parallel": true,
"self": 38.744654976910624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.14156548990809,
"count": 227665,
"is_parallel": true,
"self": 81.14156548990809
},
"communicator.exchange": {
"total": 1070.815570459168,
"count": 227665,
"is_parallel": true,
"self": 1070.815570459168
},
"steps_from_proto": {
"total": 87.0562265299402,
"count": 227665,
"is_parallel": true,
"self": 30.188224407871985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.86800212206822,
"count": 455330,
"is_parallel": true,
"self": 56.86800212206822
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 499.8877222480412,
"count": 227666,
"self": 6.809340935041973,
"children": {
"process_trajectory": {
"total": 152.10568394099937,
"count": 227666,
"self": 150.94850974599967,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1571741949996976,
"count": 10,
"self": 1.1571741949996976
}
}
},
"_update_policy": {
"total": 340.97269737199986,
"count": 95,
"self": 277.43664462599827,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.53605274600159,
"count": 2850,
"self": 63.53605274600159
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.600000001024455e-07,
"count": 1,
"self": 8.600000001024455e-07
},
"TrainerController._save_models": {
"total": 0.11075301799974113,
"count": 1,
"self": 0.0029764649998469395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10777655299989419,
"count": 1,
"self": 0.10777655299989419
}
}
}
}
}
}
}