ppo-Huggy / run_logs /timers.json
Fancellu's picture
Huggy
4d019fb verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4058208465576172,
"min": 1.4058208465576172,
"max": 1.4287124872207642,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70149.0546875,
"min": 69511.8125,
"max": 77525.21875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.27291242362526,
"min": 91.59814814814816,
"max": 423.6779661016949,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49725.0,
"min": 48942.0,
"max": 50321.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999506.0,
"min": 49570.0,
"max": 1999506.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999506.0,
"min": 49570.0,
"max": 1999506.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.370612382888794,
"min": 0.08557336032390594,
"max": 2.42698073387146,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1163.970703125,
"min": 10.012083053588867,
"max": 1253.608642578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6903615169029855,
"min": 1.9637381352929988,
"max": 3.8571402673279085,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1811.967504799366,
"min": 229.75736182928085,
"max": 1983.6909244656563,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6903615169029855,
"min": 1.9637381352929988,
"max": 3.8571402673279085,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1811.967504799366,
"min": 229.75736182928085,
"max": 1983.6909244656563,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016148942422458075,
"min": 0.012883236565782379,
"max": 0.022729256644379345,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048446827267374225,
"min": 0.025766473131564757,
"max": 0.054477928089909256,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05230343242486318,
"min": 0.02216033013537526,
"max": 0.0637467077622811,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15691029727458955,
"min": 0.04432066027075052,
"max": 0.18992960018416247,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.262148912650005e-06,
"min": 3.262148912650005e-06,
"max": 0.0002953555515481499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.786446737950016e-06,
"min": 9.786446737950016e-06,
"max": 0.0008443357685547501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108735,
"min": 0.10108735,
"max": 0.19845185000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30326205,
"min": 0.20730045,
"max": 0.5814452500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.425876500000008e-05,
"min": 6.425876500000008e-05,
"max": 0.004922747315,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019277629500000026,
"min": 0.00019277629500000026,
"max": 0.014074117975000001,
"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": "1739277687",
"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": "1739280035"
},
"total": 2348.5997239300004,
"count": 1,
"self": 0.44602951400020174,
"children": {
"run_training.setup": {
"total": 0.02333613000018886,
"count": 1,
"self": 0.02333613000018886
},
"TrainerController.start_learning": {
"total": 2348.130358286,
"count": 1,
"self": 3.9918329600004654,
"children": {
"TrainerController._reset_env": {
"total": 3.3559902550000515,
"count": 1,
"self": 3.3559902550000515
},
"TrainerController.advance": {
"total": 2340.657469208,
"count": 231613,
"self": 4.104089537326217,
"children": {
"env_step": {
"total": 1853.5126304427522,
"count": 231613,
"self": 1446.690751650151,
"children": {
"SubprocessEnvManager._take_step": {
"total": 404.28441948278805,
"count": 231613,
"self": 15.266319604793807,
"children": {
"TorchPolicy.evaluate": {
"total": 389.01809987799425,
"count": 222950,
"self": 389.01809987799425
}
}
},
"workers": {
"total": 2.53745930981313,
"count": 231613,
"self": 0.0,
"children": {
"worker_root": {
"total": 2340.9844282728586,
"count": 231613,
"is_parallel": true,
"self": 1157.5805566038016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009977980002986442,
"count": 1,
"is_parallel": true,
"self": 0.00036149100014881697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006363070001498272,
"count": 2,
"is_parallel": true,
"self": 0.0006363070001498272
}
}
},
"UnityEnvironment.step": {
"total": 0.04123137900023721,
"count": 1,
"is_parallel": true,
"self": 0.0003093580003223906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019543400003385614,
"count": 1,
"is_parallel": true,
"self": 0.00019543400003385614
},
"communicator.exchange": {
"total": 0.04007929899989904,
"count": 1,
"is_parallel": true,
"self": 0.04007929899989904
},
"steps_from_proto": {
"total": 0.000647287999981927,
"count": 1,
"is_parallel": true,
"self": 0.00019192000036127865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045536799962064833,
"count": 2,
"is_parallel": true,
"self": 0.00045536799962064833
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1183.403871669057,
"count": 231612,
"is_parallel": true,
"self": 36.28657127830229,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.1981917158796,
"count": 231612,
"is_parallel": true,
"self": 78.1981917158796
},
"communicator.exchange": {
"total": 985.135629720105,
"count": 231612,
"is_parallel": true,
"self": 985.135629720105
},
"steps_from_proto": {
"total": 83.78347895477009,
"count": 231612,
"is_parallel": true,
"self": 29.132027041719994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.651451913050096,
"count": 463224,
"is_parallel": true,
"self": 54.651451913050096
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 483.0407492279214,
"count": 231613,
"self": 5.986893034716559,
"children": {
"process_trajectory": {
"total": 146.72082750720347,
"count": 231613,
"self": 145.37814157820367,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3426859289997992,
"count": 10,
"self": 1.3426859289997992
}
}
},
"_update_policy": {
"total": 330.3330286860014,
"count": 97,
"self": 263.9305843699731,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.40244431602832,
"count": 2910,
"self": 66.40244431602832
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0320000001229346e-06,
"count": 1,
"self": 1.0320000001229346e-06
},
"TrainerController._save_models": {
"total": 0.12506483099969046,
"count": 1,
"self": 0.00189780900018377,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12316702199950669,
"count": 1,
"self": 0.12316702199950669
}
}
}
}
}
}
}