ppo-Huggy / run_logs /timers.json
greatbehzad's picture
Huggy
7ec3e0e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4017601013183594,
"min": 1.4017601013183594,
"max": 1.4270662069320679,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69528.703125,
"min": 69048.015625,
"max": 78324.8125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.62903225806451,
"min": 72.22368421052632,
"max": 392.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49370.0,
"min": 48839.0,
"max": 50299.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49987.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49987.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.500005006790161,
"min": 0.16121655702590942,
"max": 2.502896785736084,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1550.0030517578125,
"min": 20.474502563476562,
"max": 1642.1651611328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.924941018704445,
"min": 1.7744627312177748,
"max": 3.958805876049569,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2433.463431596756,
"min": 225.3567668646574,
"max": 2604.4607516527176,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.924941018704445,
"min": 1.7744627312177748,
"max": 3.958805876049569,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2433.463431596756,
"min": 225.3567668646574,
"max": 2604.4607516527176,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016209015952538014,
"min": 0.013826214949707111,
"max": 0.021968185191993447,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04862704785761404,
"min": 0.027652429899414223,
"max": 0.058184705339954235,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05417365456620852,
"min": 0.022065650516500075,
"max": 0.06999161168932914,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16252096369862556,
"min": 0.04413130103300015,
"max": 0.18674935176968574,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3214988928666635e-06,
"min": 3.3214988928666635e-06,
"max": 0.000295253176582275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.96449667859999e-06,
"min": 9.96449667859999e-06,
"max": 0.0008437768687410499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110713333333336,
"min": 0.10110713333333336,
"max": 0.19841772500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033214000000001,
"min": 0.20735305000000004,
"max": 0.58125895,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.524595333333327e-05,
"min": 6.524595333333327e-05,
"max": 0.004921044477500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019573785999999982,
"min": 0.00019573785999999982,
"max": 0.014064821605,
"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": "1710512205",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710515066"
},
"total": 2860.937141315,
"count": 1,
"self": 0.44063045900065845,
"children": {
"run_training.setup": {
"total": 0.060523070999977335,
"count": 1,
"self": 0.060523070999977335
},
"TrainerController.start_learning": {
"total": 2860.4359877849997,
"count": 1,
"self": 5.943010648938525,
"children": {
"TrainerController._reset_env": {
"total": 3.211631574000023,
"count": 1,
"self": 3.211631574000023
},
"TrainerController.advance": {
"total": 2851.1527840660615,
"count": 233070,
"self": 6.057422683040841,
"children": {
"env_step": {
"total": 2317.217241147019,
"count": 233070,
"self": 1913.4275053370945,
"children": {
"SubprocessEnvManager._take_step": {
"total": 399.72906159300584,
"count": 233070,
"self": 21.324204586054123,
"children": {
"TorchPolicy.evaluate": {
"total": 378.4048570069517,
"count": 222858,
"self": 378.4048570069517
}
}
},
"workers": {
"total": 4.0606742169187555,
"count": 233070,
"self": 0.0,
"children": {
"worker_root": {
"total": 2851.2963557679795,
"count": 233070,
"is_parallel": true,
"self": 1317.5147336589682,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010077030000275045,
"count": 1,
"is_parallel": true,
"self": 0.0002590100000361417,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007486929999913627,
"count": 2,
"is_parallel": true,
"self": 0.0007486929999913627
}
}
},
"UnityEnvironment.step": {
"total": 0.037100608999992346,
"count": 1,
"is_parallel": true,
"self": 0.003020848999994996,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002727159999835749,
"count": 1,
"is_parallel": true,
"self": 0.0002727159999835749
},
"communicator.exchange": {
"total": 0.03290871300004028,
"count": 1,
"is_parallel": true,
"self": 0.03290871300004028
},
"steps_from_proto": {
"total": 0.0008983309999734956,
"count": 1,
"is_parallel": true,
"self": 0.0002805679999937638,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006177629999797318,
"count": 2,
"is_parallel": true,
"self": 0.0006177629999797318
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1533.7816221090113,
"count": 233069,
"is_parallel": true,
"self": 45.859217658989564,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 97.64105921599923,
"count": 233069,
"is_parallel": true,
"self": 97.64105921599923
},
"communicator.exchange": {
"total": 1280.4221708889913,
"count": 233069,
"is_parallel": true,
"self": 1280.4221708889913
},
"steps_from_proto": {
"total": 109.85917434503125,
"count": 233069,
"is_parallel": true,
"self": 40.2989710369103,
"children": {
"_process_rank_one_or_two_observation": {
"total": 69.56020330812095,
"count": 466138,
"is_parallel": true,
"self": 69.56020330812095
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.8781202360015,
"count": 233070,
"self": 9.194781048821255,
"children": {
"process_trajectory": {
"total": 181.95194486418046,
"count": 233070,
"self": 180.6207119081801,
"children": {
"RLTrainer._checkpoint": {
"total": 1.331232956000349,
"count": 10,
"self": 1.331232956000349
}
}
},
"_update_policy": {
"total": 336.73139432299973,
"count": 97,
"self": 270.71570040001035,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.01569392298939,
"count": 2910,
"self": 66.01569392298939
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0439998732181266e-06,
"count": 1,
"self": 1.0439998732181266e-06
},
"TrainerController._save_models": {
"total": 0.1285604519998742,
"count": 1,
"self": 0.002178783000090334,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12638166899978387,
"count": 1,
"self": 0.12638166899978387
}
}
}
}
}
}
}