ppo-Huggy / run_logs /timers.json
Dipper00's picture
Huggy
66d4ea4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045981168746948,
"min": 1.4045981168746948,
"max": 1.4270883798599243,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69696.15625,
"min": 67969.6484375,
"max": 76884.09375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.97932330827068,
"min": 72.08479532163743,
"max": 382.89312977099235,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49465.0,
"min": 48933.0,
"max": 50159.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49741.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49741.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5358335971832275,
"min": 0.0658113956451416,
"max": 2.5493390560150146,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1349.0634765625,
"min": 8.555481910705566,
"max": 1665.9671630859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.80199686084923,
"min": 1.6281031622336462,
"max": 3.9976626015973813,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2022.6623299717903,
"min": 211.653411090374,
"max": 2638.4573170542717,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.80199686084923,
"min": 1.6281031622336462,
"max": 3.9976626015973813,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2022.6623299717903,
"min": 211.653411090374,
"max": 2638.4573170542717,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015778093589081738,
"min": 0.013598673713568132,
"max": 0.019496307973652923,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04733428076724522,
"min": 0.027197347427136264,
"max": 0.058488923920958766,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054807545989751814,
"min": 0.022348272955665986,
"max": 0.06624990484366815,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16442263796925544,
"min": 0.04469654591133197,
"max": 0.18119117319583894,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.872098709333321e-06,
"min": 3.872098709333321e-06,
"max": 0.00029535727654757504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1616296127999963e-05,
"min": 1.1616296127999963e-05,
"max": 0.0008441328186223997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129066666666668,
"min": 0.10129066666666668,
"max": 0.19845242500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30387200000000003,
"min": 0.20770675,
"max": 0.5813775999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.440426666666645e-05,
"min": 7.440426666666645e-05,
"max": 0.004922776007500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022321279999999935,
"min": 0.00022321279999999935,
"max": 0.014070742239999996,
"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": "1762323407",
"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": "1762325936"
},
"total": 2529.303962814,
"count": 1,
"self": 0.7383430319996478,
"children": {
"run_training.setup": {
"total": 0.027314552999996522,
"count": 1,
"self": 0.027314552999996522
},
"TrainerController.start_learning": {
"total": 2528.5383052290003,
"count": 1,
"self": 4.2038629040603155,
"children": {
"TrainerController._reset_env": {
"total": 2.865930002999903,
"count": 1,
"self": 2.865930002999903
},
"TrainerController.advance": {
"total": 2521.3165035629404,
"count": 233167,
"self": 4.29481658167515,
"children": {
"env_step": {
"total": 2041.4176368171265,
"count": 233167,
"self": 1639.8253119363912,
"children": {
"SubprocessEnvManager._take_step": {
"total": 398.885128339688,
"count": 233167,
"self": 15.604180439644551,
"children": {
"TorchPolicy.evaluate": {
"total": 383.28094790004343,
"count": 223032,
"self": 383.28094790004343
}
}
},
"workers": {
"total": 2.707196541047324,
"count": 233167,
"self": 0.0,
"children": {
"worker_root": {
"total": 2516.798357499963,
"count": 233167,
"is_parallel": true,
"self": 1188.1715917281272,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008956619999480608,
"count": 1,
"is_parallel": true,
"self": 0.0002374410000811622,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006582209998668986,
"count": 2,
"is_parallel": true,
"self": 0.0006582209998668986
}
}
},
"UnityEnvironment.step": {
"total": 0.03502544500042859,
"count": 1,
"is_parallel": true,
"self": 0.0003219899999749032,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020701799985545222,
"count": 1,
"is_parallel": true,
"self": 0.00020701799985545222
},
"communicator.exchange": {
"total": 0.033803678000367654,
"count": 1,
"is_parallel": true,
"self": 0.033803678000367654
},
"steps_from_proto": {
"total": 0.0006927590002305806,
"count": 1,
"is_parallel": true,
"self": 0.00019472600070002954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000498032999530551,
"count": 2,
"is_parallel": true,
"self": 0.000498032999530551
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1328.6267657718358,
"count": 233166,
"is_parallel": true,
"self": 37.97181240215696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.2495763877896,
"count": 233166,
"is_parallel": true,
"self": 81.2495763877896
},
"communicator.exchange": {
"total": 1118.61169036191,
"count": 233166,
"is_parallel": true,
"self": 1118.61169036191
},
"steps_from_proto": {
"total": 90.79368661997933,
"count": 233166,
"is_parallel": true,
"self": 32.8456106941062,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.94807592587313,
"count": 466332,
"is_parallel": true,
"self": 57.94807592587313
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 475.6040501641387,
"count": 233167,
"self": 6.375289981120204,
"children": {
"process_trajectory": {
"total": 156.43587175901712,
"count": 233167,
"self": 155.36933865201672,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0665331070003958,
"count": 10,
"self": 1.0665331070003958
}
}
},
"_update_policy": {
"total": 312.7928884240014,
"count": 97,
"self": 249.35436399899754,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.438524425003834,
"count": 2910,
"self": 63.438524425003834
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2729997251881287e-06,
"count": 1,
"self": 1.2729997251881287e-06
},
"TrainerController._save_models": {
"total": 0.15200748600000225,
"count": 1,
"self": 0.0018799990002662526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.150127486999736,
"count": 1,
"self": 0.150127486999736
}
}
}
}
}
}
}