ppo-Huggy / run_logs /timers.json
Musou's picture
Huggy
41d9681 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4026695489883423,
"min": 1.4026695489883423,
"max": 1.4254710674285889,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70711.375,
"min": 68167.359375,
"max": 78338.1171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.56457564575646,
"min": 88.49910554561717,
"max": 381.6363636363636,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50170.0,
"min": 48833.0,
"max": 50376.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999944.0,
"min": 49952.0,
"max": 1999944.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999944.0,
"min": 49952.0,
"max": 1999944.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.436542272567749,
"min": 0.11973369121551514,
"max": 2.4670374393463135,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1318.16943359375,
"min": 15.685113906860352,
"max": 1338.4647216796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.744862437578755,
"min": 1.8366957871058516,
"max": 3.888336158733742,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2025.9705787301064,
"min": 240.60714811086655,
"max": 2102.347334444523,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.744862437578755,
"min": 1.8366957871058516,
"max": 3.888336158733742,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2025.9705787301064,
"min": 240.60714811086655,
"max": 2102.347334444523,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015319995930379568,
"min": 0.013068079438623197,
"max": 0.020871438626393984,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045959987791138704,
"min": 0.026136158877246393,
"max": 0.05811089623991089,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05545249167415831,
"min": 0.02196930618956685,
"max": 0.05930202590922515,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16635747502247494,
"min": 0.0439386123791337,
"max": 0.17621457887192565,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4719488427166654e-06,
"min": 3.4719488427166654e-06,
"max": 0.00029535600154800005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0415846528149996e-05,
"min": 1.0415846528149996e-05,
"max": 0.0008441467686177499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115728333333336,
"min": 0.10115728333333336,
"max": 0.19845199999999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034718500000001,
"min": 0.2074499,
"max": 0.5813822499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.774843833333332e-05,
"min": 6.774843833333332e-05,
"max": 0.0049227548,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020324531499999997,
"min": 0.00020324531499999997,
"max": 0.014070974274999998,
"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": "1733312642",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733315138"
},
"total": 2496.144595486,
"count": 1,
"self": 0.4756869650000226,
"children": {
"run_training.setup": {
"total": 0.05891161799991096,
"count": 1,
"self": 0.05891161799991096
},
"TrainerController.start_learning": {
"total": 2495.609996903,
"count": 1,
"self": 4.7434791120563204,
"children": {
"TrainerController._reset_env": {
"total": 5.63945532400021,
"count": 1,
"self": 5.63945532400021
},
"TrainerController.advance": {
"total": 2485.1124226709426,
"count": 232051,
"self": 4.683391180856233,
"children": {
"env_step": {
"total": 1967.0912407390208,
"count": 232051,
"self": 1545.3941068980128,
"children": {
"SubprocessEnvManager._take_step": {
"total": 418.868230723044,
"count": 232051,
"self": 16.182850946072904,
"children": {
"TorchPolicy.evaluate": {
"total": 402.6853797769711,
"count": 223071,
"self": 402.6853797769711
}
}
},
"workers": {
"total": 2.828903117964046,
"count": 232051,
"self": 0.0,
"children": {
"worker_root": {
"total": 2488.184958548942,
"count": 232051,
"is_parallel": true,
"self": 1234.221180995087,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000854656999990766,
"count": 1,
"is_parallel": true,
"self": 0.00023151699974732765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006231400002434384,
"count": 2,
"is_parallel": true,
"self": 0.0006231400002434384
}
}
},
"UnityEnvironment.step": {
"total": 0.029278143000055934,
"count": 1,
"is_parallel": true,
"self": 0.0003749810000499565,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020448700001907127,
"count": 1,
"is_parallel": true,
"self": 0.00020448700001907127
},
"communicator.exchange": {
"total": 0.02795841800002563,
"count": 1,
"is_parallel": true,
"self": 0.02795841800002563
},
"steps_from_proto": {
"total": 0.0007402569999612751,
"count": 1,
"is_parallel": true,
"self": 0.00019260700014456233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005476499998167128,
"count": 2,
"is_parallel": true,
"self": 0.0005476499998167128
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1253.9637775538552,
"count": 232050,
"is_parallel": true,
"self": 37.8579076677147,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.2882172642096,
"count": 232050,
"is_parallel": true,
"self": 84.2882172642096
},
"communicator.exchange": {
"total": 1041.9787104048119,
"count": 232050,
"is_parallel": true,
"self": 1041.9787104048119
},
"steps_from_proto": {
"total": 89.83894221711898,
"count": 232050,
"is_parallel": true,
"self": 33.58490286280494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.254039354314045,
"count": 464100,
"is_parallel": true,
"self": 56.254039354314045
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 513.3377907510653,
"count": 232051,
"self": 6.755774951902822,
"children": {
"process_trajectory": {
"total": 169.23765484116348,
"count": 232051,
"self": 167.87448683416278,
"children": {
"RLTrainer._checkpoint": {
"total": 1.363168007000695,
"count": 10,
"self": 1.363168007000695
}
}
},
"_update_policy": {
"total": 337.344360957999,
"count": 97,
"self": 271.00180642499686,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.34255453300216,
"count": 2910,
"self": 66.34255453300216
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.350005711894482e-07,
"count": 1,
"self": 9.350005711894482e-07
},
"TrainerController._save_models": {
"total": 0.11463886100045784,
"count": 1,
"self": 0.002950396000414912,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11168846500004292,
"count": 1,
"self": 0.11168846500004292
}
}
}
}
}
}
}