ppo-Huggy / run_logs /timers.json
HCho's picture
Huggyletsgo
261c08b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4047363996505737,
"min": 1.4047363996505737,
"max": 1.4294191598892212,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69482.4765625,
"min": 69105.328125,
"max": 75863.6484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.18503118503118,
"min": 96.46588693957115,
"max": 420.4621848739496,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49632.0,
"min": 48888.0,
"max": 50195.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999395.0,
"min": 49405.0,
"max": 1999395.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999395.0,
"min": 49405.0,
"max": 1999395.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3490045070648193,
"min": 0.11394234746694565,
"max": 2.454404830932617,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1129.8712158203125,
"min": 13.445197105407715,
"max": 1249.448486328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6211407793039094,
"min": 1.7063311767780174,
"max": 3.8325862011069773,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1741.7687148451805,
"min": 201.34707885980606,
"max": 1882.9900615215302,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6211407793039094,
"min": 1.7063311767780174,
"max": 3.8325862011069773,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1741.7687148451805,
"min": 201.34707885980606,
"max": 1882.9900615215302,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017590619578145884,
"min": 0.013436916426548528,
"max": 0.01943241812987253,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052771858734437654,
"min": 0.02825176844295735,
"max": 0.05316345021516705,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0501872924880849,
"min": 0.02249759432549278,
"max": 0.05724373441189527,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1505618774642547,
"min": 0.04499518865098556,
"max": 0.1651175945997238,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.345948884716672e-06,
"min": 3.345948884716672e-06,
"max": 0.000295362076545975,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0037846654150016e-05,
"min": 1.0037846654150016e-05,
"max": 0.0008443504685498499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011152833333333,
"min": 0.1011152833333333,
"max": 0.19845402499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033458499999999,
"min": 0.20738174999999995,
"max": 0.58145015,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.565263833333344e-05,
"min": 6.565263833333344e-05,
"max": 0.004922855847499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019695791500000035,
"min": 0.00019695791500000035,
"max": 0.014074362485,
"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": "1735780077",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735782468"
},
"total": 2390.7714611540005,
"count": 1,
"self": 0.8177609010008382,
"children": {
"run_training.setup": {
"total": 0.07072228099968925,
"count": 1,
"self": 0.07072228099968925
},
"TrainerController.start_learning": {
"total": 2389.882977972,
"count": 1,
"self": 4.277231244186169,
"children": {
"TrainerController._reset_env": {
"total": 5.091901367999981,
"count": 1,
"self": 5.091901367999981
},
"TrainerController.advance": {
"total": 2380.3495004068136,
"count": 231154,
"self": 4.385793294973155,
"children": {
"env_step": {
"total": 1888.3927300457826,
"count": 231154,
"self": 1481.949978683656,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.8200419261425,
"count": 231154,
"self": 15.675404856146088,
"children": {
"TorchPolicy.evaluate": {
"total": 388.1446370699964,
"count": 222953,
"self": 388.1446370699964
}
}
},
"workers": {
"total": 2.622709435984234,
"count": 231154,
"self": 0.0,
"children": {
"worker_root": {
"total": 2382.7459094871947,
"count": 231154,
"is_parallel": true,
"self": 1176.6252556582372,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008549700000912708,
"count": 1,
"is_parallel": true,
"self": 0.00023947199997564894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006154980001156218,
"count": 2,
"is_parallel": true,
"self": 0.0006154980001156218
}
}
},
"UnityEnvironment.step": {
"total": 0.028763231000084488,
"count": 1,
"is_parallel": true,
"self": 0.000357596000412741,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021883499994146405,
"count": 1,
"is_parallel": true,
"self": 0.00021883499994146405
},
"communicator.exchange": {
"total": 0.02745355099978042,
"count": 1,
"is_parallel": true,
"self": 0.02745355099978042
},
"steps_from_proto": {
"total": 0.0007332489999498648,
"count": 1,
"is_parallel": true,
"self": 0.00021535199994104914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005178970000088157,
"count": 2,
"is_parallel": true,
"self": 0.0005178970000088157
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1206.1206538289575,
"count": 231153,
"is_parallel": true,
"self": 36.8275792219456,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.4273373171095,
"count": 231153,
"is_parallel": true,
"self": 79.4273373171095
},
"communicator.exchange": {
"total": 1003.7775355009958,
"count": 231153,
"is_parallel": true,
"self": 1003.7775355009958
},
"steps_from_proto": {
"total": 86.08820178890664,
"count": 231153,
"is_parallel": true,
"self": 30.46030137712387,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.627900411782775,
"count": 462306,
"is_parallel": true,
"self": 55.627900411782775
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.5709770660578,
"count": 231154,
"self": 6.054372762012463,
"children": {
"process_trajectory": {
"total": 151.1727330470403,
"count": 231154,
"self": 149.60141539403958,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5713176530007331,
"count": 10,
"self": 1.5713176530007331
}
}
},
"_update_policy": {
"total": 330.34387125700505,
"count": 97,
"self": 264.6708034280009,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.67306782900414,
"count": 2910,
"self": 65.67306782900414
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2420005077729002e-06,
"count": 1,
"self": 1.2420005077729002e-06
},
"TrainerController._save_models": {
"total": 0.16434371099967393,
"count": 1,
"self": 0.002902145999541972,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16144156500013196,
"count": 1,
"self": 0.16144156500013196
}
}
}
}
}
}
}