ppo-Huggy / run_logs /timers.json
alient12's picture
Huggy
232679b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4018083810806274,
"min": 1.4018083810806274,
"max": 1.4279298782348633,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70394.609375,
"min": 68769.3203125,
"max": 76499.8203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.43137254901961,
"min": 69.96448863636364,
"max": 403.5483870967742,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49348.0,
"min": 49255.0,
"max": 50040.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49852.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49852.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.466731548309326,
"min": 0.03963615372776985,
"max": 2.5253190994262695,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1635.4429931640625,
"min": 4.875247001647949,
"max": 1740.864013671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8428946124842085,
"min": 1.6521612241621908,
"max": 4.004744980998353,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2547.83912807703,
"min": 203.21583057194948,
"max": 2699.6332788467407,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8428946124842085,
"min": 1.6521612241621908,
"max": 4.004744980998353,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2547.83912807703,
"min": 203.21583057194948,
"max": 2699.6332788467407,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017454150924782474,
"min": 0.012631504666448261,
"max": 0.021052072641517344,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05236245277434742,
"min": 0.025263009332896522,
"max": 0.06315621792455203,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06191844008862973,
"min": 0.022930633711318177,
"max": 0.06866275239735842,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18575532026588917,
"min": 0.045861267422636354,
"max": 0.19574585333466532,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.855248714950007e-06,
"min": 3.855248714950007e-06,
"max": 0.0002953071015642999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1565746144850021e-05,
"min": 1.1565746144850021e-05,
"max": 0.0008439711186762997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128505,
"min": 0.10128505,
"max": 0.19843569999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30385515,
"min": 0.20769930000000006,
"max": 0.5813237,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.412399500000013e-05,
"min": 7.412399500000013e-05,
"max": 0.004921941429999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022237198500000036,
"min": 0.00022237198500000036,
"max": 0.014068052629999998,
"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": "1727450654",
"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": "1727453297"
},
"total": 2643.273968189,
"count": 1,
"self": 0.48982388300009916,
"children": {
"run_training.setup": {
"total": 0.051885621999872455,
"count": 1,
"self": 0.051885621999872455
},
"TrainerController.start_learning": {
"total": 2642.732258684,
"count": 1,
"self": 4.812193545030823,
"children": {
"TrainerController._reset_env": {
"total": 2.3815539929998977,
"count": 1,
"self": 2.3815539929998977
},
"TrainerController.advance": {
"total": 2635.4139427059695,
"count": 233346,
"self": 5.038892098960332,
"children": {
"env_step": {
"total": 2117.3697877400305,
"count": 233346,
"self": 1668.005538136027,
"children": {
"SubprocessEnvManager._take_step": {
"total": 446.27881426202794,
"count": 233346,
"self": 16.609013065018416,
"children": {
"TorchPolicy.evaluate": {
"total": 429.6698011970095,
"count": 222995,
"self": 429.6698011970095
}
}
},
"workers": {
"total": 3.085435341975426,
"count": 233346,
"self": 0.0,
"children": {
"worker_root": {
"total": 2635.1245124909265,
"count": 233346,
"is_parallel": true,
"self": 1287.917151450892,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008455089998733456,
"count": 1,
"is_parallel": true,
"self": 0.0002492269998128904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005962820000604552,
"count": 2,
"is_parallel": true,
"self": 0.0005962820000604552
}
}
},
"UnityEnvironment.step": {
"total": 0.029677459000140516,
"count": 1,
"is_parallel": true,
"self": 0.0003516379999837227,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018865200013351568,
"count": 1,
"is_parallel": true,
"self": 0.00018865200013351568
},
"communicator.exchange": {
"total": 0.028392992000135564,
"count": 1,
"is_parallel": true,
"self": 0.028392992000135564
},
"steps_from_proto": {
"total": 0.0007441769998877135,
"count": 1,
"is_parallel": true,
"self": 0.00019716799965863174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005470090002290817,
"count": 2,
"is_parallel": true,
"self": 0.0005470090002290817
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1347.2073610400344,
"count": 233345,
"is_parallel": true,
"self": 39.66654657074355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.58930154104951,
"count": 233345,
"is_parallel": true,
"self": 88.58930154104951
},
"communicator.exchange": {
"total": 1123.5172069901291,
"count": 233345,
"is_parallel": true,
"self": 1123.5172069901291
},
"steps_from_proto": {
"total": 95.43430593811217,
"count": 233345,
"is_parallel": true,
"self": 36.10996046311652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.32434547499565,
"count": 466690,
"is_parallel": true,
"self": 59.32434547499565
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 513.0052628669787,
"count": 233346,
"self": 6.9775484289928045,
"children": {
"process_trajectory": {
"total": 181.23694095298674,
"count": 233346,
"self": 179.81172496598674,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4252159870000014,
"count": 10,
"self": 1.4252159870000014
}
}
},
"_update_policy": {
"total": 324.79077348499914,
"count": 97,
"self": 259.81083299900115,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.97994048599799,
"count": 2910,
"self": 64.97994048599799
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3419999049801845e-06,
"count": 1,
"self": 1.3419999049801845e-06
},
"TrainerController._save_models": {
"total": 0.12456709800017052,
"count": 1,
"self": 0.0019409340002312092,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12262616399993931,
"count": 1,
"self": 0.12262616399993931
}
}
}
}
}
}
}