ppo-Huggy / run_logs /timers.json
Techdread's picture
Huggy
31514f6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4033902883529663,
"min": 1.4033902883529663,
"max": 1.424268126487732,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69087.5,
"min": 69087.5,
"max": 75809.34375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.53537284894837,
"min": 79.45088566827697,
"max": 400.672,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49442.0,
"min": 48771.0,
"max": 50164.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999942.0,
"min": 49770.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999942.0,
"min": 49770.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4473047256469727,
"min": 0.062093447893857956,
"max": 2.50179123878479,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1279.9404296875,
"min": 7.699587345123291,
"max": 1544.152587890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.745652914161208,
"min": 1.5961693837758033,
"max": 3.9468518500869685,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1958.9764741063118,
"min": 197.92500358819962,
"max": 2441.828167974949,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.745652914161208,
"min": 1.5961693837758033,
"max": 3.9468518500869685,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1958.9764741063118,
"min": 197.92500358819962,
"max": 2441.828167974949,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017907604687045223,
"min": 0.013602753030014961,
"max": 0.019081381451784788,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053722814061135674,
"min": 0.027205506060029923,
"max": 0.05558174083513828,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04906702691482173,
"min": 0.022478916992743812,
"max": 0.06391627254585425,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1472010807444652,
"min": 0.044957833985487625,
"max": 0.19021118991076946,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4949488350499936e-06,
"min": 3.4949488350499936e-06,
"max": 0.0002953383765538749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0484846505149981e-05,
"min": 1.0484846505149981e-05,
"max": 0.0008440848186384001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116494999999999,
"min": 0.10116494999999999,
"max": 0.19844612500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30349485,
"min": 0.20745825000000004,
"max": 0.5813616000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.81310049999999e-05,
"min": 6.81310049999999e-05,
"max": 0.0049224616375,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002043930149999997,
"min": 0.0002043930149999997,
"max": 0.01406994384,
"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": "1716920954",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716923561"
},
"total": 2606.786864525995,
"count": 1,
"self": 0.21875626399560133,
"children": {
"run_training.setup": {
"total": 0.04293294200033415,
"count": 1,
"self": 0.04293294200033415
},
"TrainerController.start_learning": {
"total": 2606.525175319999,
"count": 1,
"self": 5.912728971597971,
"children": {
"TrainerController._reset_env": {
"total": 1.5611207890033256,
"count": 1,
"self": 1.5611207890033256
},
"TrainerController.advance": {
"total": 2598.863219030405,
"count": 232800,
"self": 5.338609945429198,
"children": {
"env_step": {
"total": 2121.503280531906,
"count": 232800,
"self": 1430.3313972774486,
"children": {
"SubprocessEnvManager._take_step": {
"total": 687.4899153361257,
"count": 232800,
"self": 18.63789401995018,
"children": {
"TorchPolicy.evaluate": {
"total": 668.8520213161755,
"count": 222986,
"self": 668.8520213161755
}
}
},
"workers": {
"total": 3.681967918331793,
"count": 232800,
"self": 0.0,
"children": {
"worker_root": {
"total": 2596.406126671791,
"count": 232800,
"is_parallel": true,
"self": 1460.2256476178227,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006592710051336326,
"count": 1,
"is_parallel": true,
"self": 0.00014408100105356425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005151900040800683,
"count": 2,
"is_parallel": true,
"self": 0.0005151900040800683
}
}
},
"UnityEnvironment.step": {
"total": 0.014768290995561983,
"count": 1,
"is_parallel": true,
"self": 0.00019483999494696036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00012188000255264342,
"count": 1,
"is_parallel": true,
"self": 0.00012188000255264342
},
"communicator.exchange": {
"total": 0.014126250003755558,
"count": 1,
"is_parallel": true,
"self": 0.014126250003755558
},
"steps_from_proto": {
"total": 0.0003253209943068214,
"count": 1,
"is_parallel": true,
"self": 9.043999307323247e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0002348810012335889,
"count": 2,
"is_parallel": true,
"self": 0.0002348810012335889
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1136.1804790539682,
"count": 232799,
"is_parallel": true,
"self": 28.758640595144243,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 42.19989279368747,
"count": 232799,
"is_parallel": true,
"self": 42.19989279368747
},
"communicator.exchange": {
"total": 1003.0716392707109,
"count": 232799,
"is_parallel": true,
"self": 1003.0716392707109
},
"steps_from_proto": {
"total": 62.15030639442557,
"count": 232799,
"is_parallel": true,
"self": 20.631505128156277,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.51880126626929,
"count": 465598,
"is_parallel": true,
"self": 41.51880126626929
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.0213285530699,
"count": 232800,
"self": 8.818852692777,
"children": {
"process_trajectory": {
"total": 191.7227909512876,
"count": 232800,
"self": 190.1264921442853,
"children": {
"RLTrainer._checkpoint": {
"total": 1.596298807002313,
"count": 10,
"self": 1.596298807002313
}
}
},
"_update_policy": {
"total": 271.4796849090053,
"count": 97,
"self": 181.3000996540286,
"children": {
"TorchPPOOptimizer.update": {
"total": 90.1795852549767,
"count": 2910,
"self": 90.1795852549767
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1899974197149277e-06,
"count": 1,
"self": 1.1899974197149277e-06
},
"TrainerController._save_models": {
"total": 0.18810533899522852,
"count": 1,
"self": 0.0015093249967321754,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18659601399849635,
"count": 1,
"self": 0.18659601399849635
}
}
}
}
}
}
}