ppo-Huggy / run_logs /timers.json
AntonLu's picture
Huggy_bestboy
ce1db7f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4116207361221313,
"min": 1.4116207361221313,
"max": 1.430772066116333,
"count": 50
},
"Huggy.Policy.Entropy.sum": {
"value": 69766.53125,
"min": 68407.8046875,
"max": 76885.421875,
"count": 50
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.26642335766424,
"min": 86.02787456445994,
"max": 393.6377952755906,
"count": 50
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49466.0,
"min": 48655.0,
"max": 50149.0,
"count": 50
},
"Huggy.Step.mean": {
"value": 2499281.0,
"min": 49894.0,
"max": 2499281.0,
"count": 50
},
"Huggy.Step.sum": {
"value": 2499281.0,
"min": 49894.0,
"max": 2499281.0,
"count": 50
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5048789978027344,
"min": 0.1483452022075653,
"max": 2.5048789978027344,
"count": 50
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1372.6737060546875,
"min": 18.691495895385742,
"max": 1395.511474609375,
"count": 50
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8150970318021566,
"min": 1.89413540230857,
"max": 3.912285430494703,
"count": 50
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2090.673173427582,
"min": 238.66106069087982,
"max": 2133.879467666149,
"count": 50
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8150970318021566,
"min": 1.89413540230857,
"max": 3.912285430494703,
"count": 50
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2090.673173427582,
"min": 238.66106069087982,
"max": 2133.879467666149,
"count": 50
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01882675220953792,
"min": 0.012829927081475033,
"max": 0.018953186580135176,
"count": 50
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.056480256628613765,
"min": 0.025659854162950066,
"max": 0.05666990419267677,
"count": 50
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04682487179007796,
"min": 0.021427530050277713,
"max": 0.06198042059938113,
"count": 50
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14047461537023387,
"min": 0.043406547792255876,
"max": 0.17245404856900373,
"count": 50
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2260189246933394e-06,
"min": 3.2260189246933394e-06,
"max": 0.00029622048125983996,
"count": 50
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.678056774080018e-06,
"min": 9.678056774080018e-06,
"max": 0.0008551641749452799,
"count": 50
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107530666666668,
"min": 0.10107530666666668,
"max": 0.19874015999999994,
"count": 50
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30322592000000004,
"min": 0.20628684000000005,
"max": 0.5850547200000001,
"count": 50
},
"Huggy.Policy.Beta.mean": {
"value": 7.441086933333343e-05,
"min": 7.441086933333343e-05,
"max": 0.005924535583999999,
"count": 50
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002232326080000003,
"min": 0.0002232326080000003,
"max": 0.017104777727999995,
"count": 50
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750766576",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750770661"
},
"total": 4084.684970749,
"count": 1,
"self": 0.5939943190001031,
"children": {
"run_training.setup": {
"total": 0.03340281599997752,
"count": 1,
"self": 0.03340281599997752
},
"TrainerController.start_learning": {
"total": 4084.057573614,
"count": 1,
"self": 5.882704825053224,
"children": {
"TrainerController._reset_env": {
"total": 3.7811648420000097,
"count": 1,
"self": 3.7811648420000097
},
"TrainerController.advance": {
"total": 4074.3012613019464,
"count": 290305,
"self": 6.050381205837766,
"children": {
"env_step": {
"total": 2466.7628412122344,
"count": 290305,
"self": 2108.0152660871745,
"children": {
"SubprocessEnvManager._take_step": {
"total": 355.03368228999005,
"count": 290305,
"self": 21.310155843723635,
"children": {
"TorchPolicy.evaluate": {
"total": 333.7235264462664,
"count": 278624,
"self": 333.7235264462664
}
}
},
"workers": {
"total": 3.7138928350699985,
"count": 290305,
"self": 0.0,
"children": {
"worker_root": {
"total": 4073.7699195769405,
"count": 290305,
"is_parallel": true,
"self": 2357.799465996869,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012355530000149884,
"count": 1,
"is_parallel": true,
"self": 0.00035503300000527815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008805200000097102,
"count": 2,
"is_parallel": true,
"self": 0.0008805200000097102
}
}
},
"UnityEnvironment.step": {
"total": 0.03266233300001886,
"count": 1,
"is_parallel": true,
"self": 0.0003396020000536737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002545410000038828,
"count": 1,
"is_parallel": true,
"self": 0.0002545410000038828
},
"communicator.exchange": {
"total": 0.03130108099998097,
"count": 1,
"is_parallel": true,
"self": 0.03130108099998097
},
"steps_from_proto": {
"total": 0.0007671089999803371,
"count": 1,
"is_parallel": true,
"self": 0.00019773299999314986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005693759999871872,
"count": 2,
"is_parallel": true,
"self": 0.0005693759999871872
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1715.9704535800715,
"count": 290304,
"is_parallel": true,
"self": 53.170618558729984,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 114.10426279813476,
"count": 290304,
"is_parallel": true,
"self": 114.10426279813476
},
"communicator.exchange": {
"total": 1426.0551713601205,
"count": 290304,
"is_parallel": true,
"self": 1426.0551713601205
},
"steps_from_proto": {
"total": 122.64040086308603,
"count": 290304,
"is_parallel": true,
"self": 43.084168180233576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.55623268285245,
"count": 580608,
"is_parallel": true,
"self": 79.55623268285245
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1601.488038883874,
"count": 290305,
"self": 8.599475134889417,
"children": {
"process_trajectory": {
"total": 250.52711180898524,
"count": 290305,
"self": 249.16365344298464,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3634583660006,
"count": 12,
"self": 1.3634583660006
}
}
},
"_update_policy": {
"total": 1342.3614519399994,
"count": 121,
"self": 349.54152803300326,
"children": {
"TorchPPOOptimizer.update": {
"total": 992.8199239069961,
"count": 3630,
"self": 992.8199239069961
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.499999578110874e-07,
"count": 1,
"self": 9.499999578110874e-07
},
"TrainerController._save_models": {
"total": 0.09244169500016142,
"count": 1,
"self": 0.0023243189998538583,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09011737600030756,
"count": 1,
"self": 0.09011737600030756
}
}
}
}
}
}
}