ppo-Huggy / run_logs /timers.json
earlzero's picture
Huggy
00abe4f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401651382446289,
"min": 1.401651382446289,
"max": 1.4224117994308472,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70923.5625,
"min": 67807.1015625,
"max": 78727.5546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.06938775510204,
"min": 90.94659300184162,
"max": 397.53543307086613,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49034.0,
"min": 48883.0,
"max": 50487.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49948.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49948.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.345715045928955,
"min": -0.006194692105054855,
"max": 2.4175074100494385,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1149.400390625,
"min": -0.7805312275886536,
"max": 1312.70654296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5986637473106384,
"min": 1.8408102274887146,
"max": 3.885445510704434,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1763.3452361822128,
"min": 231.94208866357803,
"max": 2109.7969123125076,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5986637473106384,
"min": 1.8408102274887146,
"max": 3.885445510704434,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1763.3452361822128,
"min": 231.94208866357803,
"max": 2109.7969123125076,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018655541857070704,
"min": 0.014280417750362378,
"max": 0.019840014777582838,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05596662557121211,
"min": 0.028579252904940705,
"max": 0.05596662557121211,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054482677413357626,
"min": 0.021954970061779024,
"max": 0.05908600048472484,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16344803224007287,
"min": 0.04390994012355805,
"max": 0.16956281525393327,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.266398911233333e-06,
"min": 3.266398911233333e-06,
"max": 0.00029533515155495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.7991967337e-06,
"min": 9.7991967337e-06,
"max": 0.0008441551686149501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010887666666667,
"min": 0.1010887666666667,
"max": 0.19844505,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032663000000001,
"min": 0.20733725000000003,
"max": 0.58138505,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.432945666666667e-05,
"min": 6.432945666666667e-05,
"max": 0.004922407995000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019298837000000002,
"min": 0.00019298837000000002,
"max": 0.014071113995,
"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": "1726856093",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726858644"
},
"total": 2551.0474350219997,
"count": 1,
"self": 0.4343757840001672,
"children": {
"run_training.setup": {
"total": 0.06284925599999269,
"count": 1,
"self": 0.06284925599999269
},
"TrainerController.start_learning": {
"total": 2550.5502099819996,
"count": 1,
"self": 4.362759126038782,
"children": {
"TrainerController._reset_env": {
"total": 2.5853220330000113,
"count": 1,
"self": 2.5853220330000113
},
"TrainerController.advance": {
"total": 2543.4890775059603,
"count": 231372,
"self": 4.753734467074537,
"children": {
"env_step": {
"total": 2009.428026346932,
"count": 231372,
"self": 1587.5072600878589,
"children": {
"SubprocessEnvManager._take_step": {
"total": 419.0817101799794,
"count": 231372,
"self": 15.640649656011817,
"children": {
"TorchPolicy.evaluate": {
"total": 403.44106052396756,
"count": 223000,
"self": 403.44106052396756
}
}
},
"workers": {
"total": 2.8390560790937798,
"count": 231372,
"self": 0.0,
"children": {
"worker_root": {
"total": 2543.1455589348348,
"count": 231372,
"is_parallel": true,
"self": 1255.8933974957774,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007978760000355578,
"count": 1,
"is_parallel": true,
"self": 0.0002208120000659619,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005770639999695959,
"count": 2,
"is_parallel": true,
"self": 0.0005770639999695959
}
}
},
"UnityEnvironment.step": {
"total": 0.07068109599998706,
"count": 1,
"is_parallel": true,
"self": 0.00040683000003127745,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019572700000480836,
"count": 1,
"is_parallel": true,
"self": 0.00019572700000480836
},
"communicator.exchange": {
"total": 0.06930429199996979,
"count": 1,
"is_parallel": true,
"self": 0.06930429199996979
},
"steps_from_proto": {
"total": 0.0007742469999811874,
"count": 1,
"is_parallel": true,
"self": 0.0002292949999969096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005449519999842778,
"count": 2,
"is_parallel": true,
"self": 0.0005449519999842778
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1287.2521614390573,
"count": 231371,
"is_parallel": true,
"self": 38.84987486906698,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.91881734601611,
"count": 231371,
"is_parallel": true,
"self": 85.91881734601611
},
"communicator.exchange": {
"total": 1071.3465528409995,
"count": 231371,
"is_parallel": true,
"self": 1071.3465528409995
},
"steps_from_proto": {
"total": 91.13691638297473,
"count": 231371,
"is_parallel": true,
"self": 34.590921270982506,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.54599511199223,
"count": 462742,
"is_parallel": true,
"self": 56.54599511199223
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 529.3073166919538,
"count": 231372,
"self": 6.87252029388867,
"children": {
"process_trajectory": {
"total": 157.9094180620657,
"count": 231372,
"self": 156.5267488880654,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3826691740002843,
"count": 10,
"self": 1.3826691740002843
}
}
},
"_update_policy": {
"total": 364.5253783359994,
"count": 97,
"self": 294.1822556800133,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.34312265598606,
"count": 2910,
"self": 70.34312265598606
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5660002645745408e-06,
"count": 1,
"self": 1.5660002645745408e-06
},
"TrainerController._save_models": {
"total": 0.11304975100028969,
"count": 1,
"self": 0.001797370000531373,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11125238099975832,
"count": 1,
"self": 0.11125238099975832
}
}
}
}
}
}
}