ppo-Huggy / run_logs /timers.json
ezzzeee's picture
Huggy
27efdde verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4082449674606323,
"min": 1.4082449674606323,
"max": 1.4309923648834229,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71143.125,
"min": 68323.7734375,
"max": 77784.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.76164874551971,
"min": 81.78311258278146,
"max": 385.10769230769233,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49529.0,
"min": 49086.0,
"max": 50096.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999351.0,
"min": 49930.0,
"max": 1999351.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999351.0,
"min": 49930.0,
"max": 1999351.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.495037317276001,
"min": 0.13231073319911957,
"max": 2.495037317276001,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1392.2308349609375,
"min": 17.068084716796875,
"max": 1455.0206298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.949910766975854,
"min": 1.9102133956066398,
"max": 3.9538925232558415,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2204.0502079725266,
"min": 246.41752803325653,
"max": 2343.609392642975,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.949910766975854,
"min": 1.9102133956066398,
"max": 3.9538925232558415,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2204.0502079725266,
"min": 246.41752803325653,
"max": 2343.609392642975,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01716715218337615,
"min": 0.01351500730670523,
"max": 0.020806896584205484,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05150145655012845,
"min": 0.02703001461341046,
"max": 0.05712506471245433,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05519644307593505,
"min": 0.021690774522721765,
"max": 0.06030421021083991,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16558932922780514,
"min": 0.04338154904544353,
"max": 0.17670270428061485,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5417488194500083e-06,
"min": 3.5417488194500083e-06,
"max": 0.000295340626553125,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0625246458350025e-05,
"min": 1.0625246458350025e-05,
"max": 0.0008438382187205999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118054999999998,
"min": 0.10118054999999998,
"max": 0.19844687500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354164999999994,
"min": 0.20749374999999998,
"max": 0.5812794,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.890944500000013e-05,
"min": 6.890944500000013e-05,
"max": 0.0049224990625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020672833500000039,
"min": 0.00020672833500000039,
"max": 0.014065842060000004,
"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": "1743026226",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743028701"
},
"total": 2474.5180298960004,
"count": 1,
"self": 0.5372105930005091,
"children": {
"run_training.setup": {
"total": 0.02304706899985831,
"count": 1,
"self": 0.02304706899985831
},
"TrainerController.start_learning": {
"total": 2473.957772234,
"count": 1,
"self": 4.596251586938251,
"children": {
"TrainerController._reset_env": {
"total": 3.0769029090001823,
"count": 1,
"self": 3.0769029090001823
},
"TrainerController.advance": {
"total": 2466.1024183970617,
"count": 232450,
"self": 4.8901603760996295,
"children": {
"env_step": {
"total": 1982.2856594250209,
"count": 232450,
"self": 1550.3412364689116,
"children": {
"SubprocessEnvManager._take_step": {
"total": 429.2284308320882,
"count": 232450,
"self": 15.676874520144565,
"children": {
"TorchPolicy.evaluate": {
"total": 413.5515563119436,
"count": 222973,
"self": 413.5515563119436
}
}
},
"workers": {
"total": 2.7159921240211133,
"count": 232450,
"self": 0.0,
"children": {
"worker_root": {
"total": 2466.2486923271194,
"count": 232450,
"is_parallel": true,
"self": 1201.6752551921663,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014216189999842754,
"count": 1,
"is_parallel": true,
"self": 0.000581247000127405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008403719998568704,
"count": 2,
"is_parallel": true,
"self": 0.0008403719998568704
}
}
},
"UnityEnvironment.step": {
"total": 0.03248035299998264,
"count": 1,
"is_parallel": true,
"self": 0.0003246969999963767,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018689800003812707,
"count": 1,
"is_parallel": true,
"self": 0.00018689800003812707
},
"communicator.exchange": {
"total": 0.03129228299985698,
"count": 1,
"is_parallel": true,
"self": 0.03129228299985698
},
"steps_from_proto": {
"total": 0.000676475000091159,
"count": 1,
"is_parallel": true,
"self": 0.00017826900034378923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004982059997473698,
"count": 2,
"is_parallel": true,
"self": 0.0004982059997473698
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1264.573437134953,
"count": 232449,
"is_parallel": true,
"self": 37.49261046496895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.81558171396864,
"count": 232449,
"is_parallel": true,
"self": 82.81558171396864
},
"communicator.exchange": {
"total": 1055.431056345089,
"count": 232449,
"is_parallel": true,
"self": 1055.431056345089
},
"steps_from_proto": {
"total": 88.8341886109265,
"count": 232449,
"is_parallel": true,
"self": 32.922221703854575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.91196690707193,
"count": 464898,
"is_parallel": true,
"self": 55.91196690707193
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 478.9265985959412,
"count": 232450,
"self": 7.089202101885803,
"children": {
"process_trajectory": {
"total": 168.4149077590555,
"count": 232450,
"self": 167.05278206205526,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3621256970002378,
"count": 10,
"self": 1.3621256970002378
}
}
},
"_update_policy": {
"total": 303.4224887349999,
"count": 97,
"self": 238.58970388400303,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.83278485099686,
"count": 2910,
"self": 64.83278485099686
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.231999704032205e-06,
"count": 1,
"self": 1.231999704032205e-06
},
"TrainerController._save_models": {
"total": 0.18219810900018274,
"count": 1,
"self": 0.0027385400003367977,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17945956899984594,
"count": 1,
"self": 0.17945956899984594
}
}
}
}
}
}
}