ppo-Huggy / run_logs /timers.json
amihk's picture
Huggy
8f8205f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.39492928981781,
"min": 1.39492928981781,
"max": 1.4245816469192505,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68726.7734375,
"min": 68726.7734375,
"max": 75133.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.51439539347409,
"min": 78.43879173290938,
"max": 397.2142857142857,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49763.0,
"min": 49202.0,
"max": 50049.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999492.0,
"min": 49856.0,
"max": 1999492.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999492.0,
"min": 49856.0,
"max": 1999492.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.45719051361084,
"min": 0.089262954890728,
"max": 2.485341787338257,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1277.739013671875,
"min": 11.157869338989258,
"max": 1516.07177734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.830939435500365,
"min": 1.8473997383117675,
"max": 3.991206802722714,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1992.0885064601898,
"min": 230.92496728897095,
"max": 2410.9194531440735,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.830939435500365,
"min": 1.8473997383117675,
"max": 3.991206802722714,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1992.0885064601898,
"min": 230.92496728897095,
"max": 2410.9194531440735,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016058911342730024,
"min": 0.012966321234610709,
"max": 0.020600178149955656,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04817673402819007,
"min": 0.028479382431153985,
"max": 0.06091690222965553,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0526740857710441,
"min": 0.022333343233913183,
"max": 0.06218838480611642,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1580222573131323,
"min": 0.044666686467826365,
"max": 0.17444192469120026,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.534048822016652e-06,
"min": 3.534048822016652e-06,
"max": 0.00029531175156275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0602146466049956e-05,
"min": 1.0602146466049956e-05,
"max": 0.0008441814186062001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117798333333335,
"min": 0.10117798333333335,
"max": 0.19843725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353395000000005,
"min": 0.2075114,
"max": 0.5813938000000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.87813683333331e-05,
"min": 6.87813683333331e-05,
"max": 0.004922018775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020634410499999932,
"min": 0.00020634410499999932,
"max": 0.014071550619999998,
"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": "1760073410",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760075960"
},
"total": 2550.154177286,
"count": 1,
"self": 0.43666745300015464,
"children": {
"run_training.setup": {
"total": 0.02623475700011113,
"count": 1,
"self": 0.02623475700011113
},
"TrainerController.start_learning": {
"total": 2549.691275076,
"count": 1,
"self": 4.189136135071749,
"children": {
"TrainerController._reset_env": {
"total": 3.322285023000063,
"count": 1,
"self": 3.322285023000063
},
"TrainerController.advance": {
"total": 2542.0789553989284,
"count": 232932,
"self": 4.249749224989046,
"children": {
"env_step": {
"total": 2070.004784624819,
"count": 232932,
"self": 1666.8530924268237,
"children": {
"SubprocessEnvManager._take_step": {
"total": 400.4794741260281,
"count": 232932,
"self": 14.940977993129536,
"children": {
"TorchPolicy.evaluate": {
"total": 385.53849613289856,
"count": 222934,
"self": 385.53849613289856
}
}
},
"workers": {
"total": 2.6722180719672224,
"count": 232932,
"self": 0.0,
"children": {
"worker_root": {
"total": 2537.009931477002,
"count": 232932,
"is_parallel": true,
"self": 1185.6978755249431,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008366979999436808,
"count": 1,
"is_parallel": true,
"self": 0.0002672389999816005,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005694589999620803,
"count": 2,
"is_parallel": true,
"self": 0.0005694589999620803
}
}
},
"UnityEnvironment.step": {
"total": 0.03948178899997856,
"count": 1,
"is_parallel": true,
"self": 0.0003310390000024199,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018728999998529616,
"count": 1,
"is_parallel": true,
"self": 0.00018728999998529616
},
"communicator.exchange": {
"total": 0.03808362699999179,
"count": 1,
"is_parallel": true,
"self": 0.03808362699999179
},
"steps_from_proto": {
"total": 0.0008798329999990528,
"count": 1,
"is_parallel": true,
"self": 0.0002164780000839528,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006633549999151,
"count": 2,
"is_parallel": true,
"self": 0.0006633549999151
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1351.3120559520587,
"count": 232931,
"is_parallel": true,
"self": 37.379910453836146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.97052668310016,
"count": 232931,
"is_parallel": true,
"self": 80.97052668310016
},
"communicator.exchange": {
"total": 1144.633690201114,
"count": 232931,
"is_parallel": true,
"self": 1144.633690201114
},
"steps_from_proto": {
"total": 88.32792861400844,
"count": 232931,
"is_parallel": true,
"self": 31.73418081792579,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.59374779608265,
"count": 465862,
"is_parallel": true,
"self": 56.59374779608265
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 467.82442154912064,
"count": 232932,
"self": 6.34669428695679,
"children": {
"process_trajectory": {
"total": 152.3319234081639,
"count": 232932,
"self": 151.05245261716345,
"children": {
"RLTrainer._checkpoint": {
"total": 1.279470791000449,
"count": 10,
"self": 1.279470791000449
}
}
},
"_update_policy": {
"total": 309.14580385399995,
"count": 97,
"self": 246.71377086299583,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.43203299100412,
"count": 2910,
"self": 62.43203299100412
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.539999155094847e-07,
"count": 1,
"self": 9.539999155094847e-07
},
"TrainerController._save_models": {
"total": 0.10089756499974101,
"count": 1,
"self": 0.0013194129996918491,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09957815200004916,
"count": 1,
"self": 0.09957815200004916
}
}
}
}
}
}
}