ppo-Huggy / run_logs /timers.json
LuisChDev's picture
add Huggy model
a530bf2
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4075291156768799,
"min": 1.4075291156768799,
"max": 1.4276504516601562,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68522.7421875,
"min": 68522.7421875,
"max": 77388.421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.82180293501048,
"min": 85.3258232235702,
"max": 396.9685039370079,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49523.0,
"min": 49233.0,
"max": 50415.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999293.0,
"min": 49888.0,
"max": 1999293.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999293.0,
"min": 49888.0,
"max": 1999293.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3575122356414795,
"min": 0.00046062967157922685,
"max": 2.4678118228912354,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1124.5333251953125,
"min": 0.058039337396621704,
"max": 1327.569091796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6651779545678034,
"min": 1.8052288622610153,
"max": 3.907910831692149,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1748.2898843288422,
"min": 227.45883664488792,
"max": 2067.8989362716675,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6651779545678034,
"min": 1.8052288622610153,
"max": 3.907910831692149,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1748.2898843288422,
"min": 227.45883664488792,
"max": 2067.8989362716675,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016636878688910253,
"min": 0.01411370242583669,
"max": 0.020135430740063184,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049910636066730754,
"min": 0.028345973328881276,
"max": 0.06040629222018955,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04926929362118245,
"min": 0.023347481495390336,
"max": 0.05905226146181425,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14780788086354735,
"min": 0.04669496299078067,
"max": 0.17715678438544274,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1874989375333295e-06,
"min": 3.1874989375333295e-06,
"max": 0.0002953359015547,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.562496812599988e-06,
"min": 9.562496812599988e-06,
"max": 0.00084405436864855,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010624666666667,
"min": 0.1010624666666667,
"max": 0.1984453,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031874000000001,
"min": 0.2072759,
"max": 0.58135145,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.30170866666666e-05,
"min": 6.30170866666666e-05,
"max": 0.004922420469999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001890512599999998,
"min": 0.0001890512599999998,
"max": 0.014069437354999999,
"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": "1695055809",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1695058221"
},
"total": 2411.586941102,
"count": 1,
"self": 0.7879237310003191,
"children": {
"run_training.setup": {
"total": 0.043407692999608116,
"count": 1,
"self": 0.043407692999608116
},
"TrainerController.start_learning": {
"total": 2410.755609678,
"count": 1,
"self": 4.355392038990431,
"children": {
"TrainerController._reset_env": {
"total": 4.08482263399992,
"count": 1,
"self": 4.08482263399992
},
"TrainerController.advance": {
"total": 2402.12230302701,
"count": 231691,
"self": 4.350104137969993,
"children": {
"env_step": {
"total": 1846.3394777029425,
"count": 231691,
"self": 1558.948353425791,
"children": {
"SubprocessEnvManager._take_step": {
"total": 284.54452456101444,
"count": 231691,
"self": 16.7738306928959,
"children": {
"TorchPolicy.evaluate": {
"total": 267.77069386811854,
"count": 222887,
"self": 267.77069386811854
}
}
},
"workers": {
"total": 2.846599716137007,
"count": 231691,
"self": 0.0,
"children": {
"worker_root": {
"total": 2403.175321937831,
"count": 231691,
"is_parallel": true,
"self": 1130.729312603733,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009088239999073267,
"count": 1,
"is_parallel": true,
"self": 0.0002341680001336499,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006746559997736767,
"count": 2,
"is_parallel": true,
"self": 0.0006746559997736767
}
}
},
"UnityEnvironment.step": {
"total": 0.029073404999962804,
"count": 1,
"is_parallel": true,
"self": 0.00033119499994427315,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024892300007195445,
"count": 1,
"is_parallel": true,
"self": 0.00024892300007195445
},
"communicator.exchange": {
"total": 0.027743807999740966,
"count": 1,
"is_parallel": true,
"self": 0.027743807999740966
},
"steps_from_proto": {
"total": 0.0007494790002056106,
"count": 1,
"is_parallel": true,
"self": 0.00019491300054141902,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005545659996641916,
"count": 2,
"is_parallel": true,
"self": 0.0005545659996641916
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.446009334098,
"count": 231690,
"is_parallel": true,
"self": 39.39255685701755,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.18359344691862,
"count": 231690,
"is_parallel": true,
"self": 81.18359344691862
},
"communicator.exchange": {
"total": 1054.7801128710385,
"count": 231690,
"is_parallel": true,
"self": 1054.7801128710385
},
"steps_from_proto": {
"total": 97.08974615912348,
"count": 231690,
"is_parallel": true,
"self": 34.503976029314344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.585770129809134,
"count": 463380,
"is_parallel": true,
"self": 62.585770129809134
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 551.4327211860973,
"count": 231691,
"self": 6.475259178252145,
"children": {
"process_trajectory": {
"total": 133.7083784878455,
"count": 231691,
"self": 132.203543687845,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5048348000004808,
"count": 10,
"self": 1.5048348000004808
}
}
},
"_update_policy": {
"total": 411.24908351999966,
"count": 97,
"self": 351.0855088869703,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.163574633029384,
"count": 2910,
"self": 60.163574633029384
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4830002328380942e-06,
"count": 1,
"self": 1.4830002328380942e-06
},
"TrainerController._save_models": {
"total": 0.1930904949995238,
"count": 1,
"self": 0.006897741999637219,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18619275299988658,
"count": 1,
"self": 0.18619275299988658
}
}
}
}
}
}
}