ppo-Pyramids / run_logs /timers.json
jay-yeo's picture
First commit
1c82f86 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4297279715538025,
"min": 0.4297279715538025,
"max": 1.4646048545837402,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12754.326171875,
"min": 12754.326171875,
"max": 44430.25390625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989873.0,
"min": 29952.0,
"max": 989873.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989873.0,
"min": 29952.0,
"max": 989873.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5820909142494202,
"min": -0.09810417145490646,
"max": 0.5820909142494202,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 162.4033660888672,
"min": -23.643104553222656,
"max": 162.4033660888672,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014826126396656036,
"min": -0.005625404883176088,
"max": 0.3133999705314636,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.136489391326904,
"min": -1.4119765758514404,
"max": 74.27579498291016,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06983427820442659,
"min": 0.06360559005418914,
"max": 0.07371291399074795,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0475141730663988,
"min": 0.5135223698610275,
"max": 1.0475141730663988,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013533499728267392,
"min": 0.0010823064679412958,
"max": 0.016064752465086606,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20300249592401087,
"min": 0.014069984083236847,
"max": 0.22816255288974693,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.470257509946665e-06,
"min": 7.470257509946665e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011205386264919998,
"min": 0.00011205386264919998,
"max": 0.0033725935758022,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249005333333333,
"min": 0.10249005333333333,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5373508,
"min": 1.3886848,
"max": 2.4443104,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000258756328,
"min": 0.000258756328,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038813449200000003,
"min": 0.0038813449200000003,
"max": 0.11243736022,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00891244225203991,
"min": 0.008893648162484169,
"max": 0.3340936303138733,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1336866319179535,
"min": 0.12451107054948807,
"max": 2.338655471801758,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 336.5681818181818,
"min": 336.5681818181818,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29618.0,
"min": 15984.0,
"max": 32941.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6634318024258723,
"min": -1.0000000521540642,
"max": 1.6634318024258723,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 146.38199861347675,
"min": -29.9990017041564,
"max": 146.38199861347675,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6634318024258723,
"min": -1.0000000521540642,
"max": 1.6634318024258723,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 146.38199861347675,
"min": -29.9990017041564,
"max": 146.38199861347675,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.030984042347054954,
"min": 0.030984042347054954,
"max": 7.02785789500922,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.726595726540836,
"min": 2.726595726540836,
"max": 112.44572632014751,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1764328913",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/jay/anaconda3/envs/huggingface-rl/bin/mlagents-learn /home/jay/Workspace/tmp/huggingface-rl-course/Unit 5/ml-agents/config/ppo/PyramidsRND.yaml --env=/home/jay/Workspace/tmp/huggingface-rl-course/Unit 5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1764330062"
},
"total": 1148.5768240739126,
"count": 1,
"self": 0.26878284802660346,
"children": {
"run_training.setup": {
"total": 0.04142829100601375,
"count": 1,
"self": 0.04142829100601375
},
"TrainerController.start_learning": {
"total": 1148.26661293488,
"count": 1,
"self": 1.2815118483267725,
"children": {
"TrainerController._reset_env": {
"total": 1.9785449840128422,
"count": 1,
"self": 1.9785449840128422
},
"TrainerController.advance": {
"total": 1144.9416925334372,
"count": 63788,
"self": 1.097218771930784,
"children": {
"env_step": {
"total": 707.2404654850252,
"count": 63788,
"self": 577.1620528909843,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.23732025618665,
"count": 63788,
"self": 3.096741566900164,
"children": {
"TorchPolicy.evaluate": {
"total": 126.14057868928649,
"count": 62575,
"self": 126.14057868928649
}
}
},
"workers": {
"total": 0.8410923378542066,
"count": 63788,
"self": 0.0,
"children": {
"worker_root": {
"total": 1146.5324825928546,
"count": 63788,
"is_parallel": true,
"self": 647.279317652341,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001560684060677886,
"count": 1,
"is_parallel": true,
"self": 0.00041249231435358524,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011481917463243008,
"count": 8,
"is_parallel": true,
"self": 0.0011481917463243008
}
}
},
"UnityEnvironment.step": {
"total": 0.025580822955816984,
"count": 1,
"is_parallel": true,
"self": 0.00023907492868602276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021404586732387543,
"count": 1,
"is_parallel": true,
"self": 0.00021404586732387543
},
"communicator.exchange": {
"total": 0.024316081078723073,
"count": 1,
"is_parallel": true,
"self": 0.024316081078723073
},
"steps_from_proto": {
"total": 0.000811621081084013,
"count": 1,
"is_parallel": true,
"self": 0.00017693638801574707,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006346846930682659,
"count": 8,
"is_parallel": true,
"self": 0.0006346846930682659
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 499.25316494051367,
"count": 63787,
"is_parallel": true,
"self": 15.546048061456531,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.573180650360882,
"count": 63787,
"is_parallel": true,
"self": 11.573180650360882
},
"communicator.exchange": {
"total": 428.54348472249694,
"count": 63787,
"is_parallel": true,
"self": 428.54348472249694
},
"steps_from_proto": {
"total": 43.590451506199315,
"count": 63787,
"is_parallel": true,
"self": 10.1169150210917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.473536485107616,
"count": 510296,
"is_parallel": true,
"self": 33.473536485107616
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 436.6040082764812,
"count": 63788,
"self": 2.729990804102272,
"children": {
"process_trajectory": {
"total": 87.02516031661071,
"count": 63788,
"self": 86.88841006858274,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13675024802796543,
"count": 2,
"self": 0.13675024802796543
}
}
},
"_update_policy": {
"total": 346.8488571557682,
"count": 446,
"self": 182.5833819792606,
"children": {
"TorchPPOOptimizer.update": {
"total": 164.2654751765076,
"count": 22758,
"self": 164.2654751765076
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.420312613248825e-07,
"count": 1,
"self": 7.420312613248825e-07
},
"TrainerController._save_models": {
"total": 0.06486282707192004,
"count": 1,
"self": 0.0012719340156763792,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06359089305624366,
"count": 1,
"self": 0.06359089305624366
}
}
}
}
}
}
}