ppo-Huggy / run_logs /timers.json
antnaumov's picture
Huggy
47c967f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.410128116607666,
"min": 1.410128116607666,
"max": 1.4309816360473633,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70011.453125,
"min": 69517.2890625,
"max": 76740.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 120.32613908872902,
"min": 96.3859649122807,
"max": 382.9236641221374,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50176.0,
"min": 48974.0,
"max": 50176.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999889.0,
"min": 49908.0,
"max": 1999889.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999889.0,
"min": 49908.0,
"max": 1999889.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.293570041656494,
"min": 0.15502484142780304,
"max": 2.361307382583618,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 956.418701171875,
"min": 20.153228759765625,
"max": 1192.3597412109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5133178700074303,
"min": 1.898894262084594,
"max": 3.8208332558052014,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1465.0535517930984,
"min": 246.85625407099724,
"max": 1929.0896899104118,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5133178700074303,
"min": 1.898894262084594,
"max": 3.8208332558052014,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1465.0535517930984,
"min": 246.85625407099724,
"max": 1929.0896899104118,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017363747228147177,
"min": 0.014300471622118494,
"max": 0.019878446001954826,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05209124168444153,
"min": 0.02860094324423699,
"max": 0.05955969999583128,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04291995929347144,
"min": 0.02188618586709102,
"max": 0.07138519249856472,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12875987788041432,
"min": 0.04377237173418204,
"max": 0.1927223148445288,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1897989367666744e-06,
"min": 3.1897989367666744e-06,
"max": 0.000295326826557725,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.569396810300023e-06,
"min": 9.569396810300023e-06,
"max": 0.0008441941686019502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10106323333333335,
"min": 0.10106323333333335,
"max": 0.198442275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30318970000000006,
"min": 0.20730814999999997,
"max": 0.58139805,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.305534333333346e-05,
"min": 6.305534333333346e-05,
"max": 0.0049222695225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018916603000000037,
"min": 0.00018916603000000037,
"max": 0.014071762695000002,
"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": "1740916848",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740919277"
},
"total": 2428.947320655,
"count": 1,
"self": 0.4394683069999701,
"children": {
"run_training.setup": {
"total": 0.02288596599998982,
"count": 1,
"self": 0.02288596599998982
},
"TrainerController.start_learning": {
"total": 2428.484966382,
"count": 1,
"self": 4.382479337026325,
"children": {
"TrainerController._reset_env": {
"total": 3.1300772100000245,
"count": 1,
"self": 3.1300772100000245
},
"TrainerController.advance": {
"total": 2420.858047331974,
"count": 231093,
"self": 4.405417184049384,
"children": {
"env_step": {
"total": 1943.1893771079892,
"count": 231093,
"self": 1519.3256131150206,
"children": {
"SubprocessEnvManager._take_step": {
"total": 421.21241676805477,
"count": 231093,
"self": 15.376052103121538,
"children": {
"TorchPolicy.evaluate": {
"total": 405.8363646649332,
"count": 222968,
"self": 405.8363646649332
}
}
},
"workers": {
"total": 2.651347224913877,
"count": 231093,
"self": 0.0,
"children": {
"worker_root": {
"total": 2421.0237213820083,
"count": 231093,
"is_parallel": true,
"self": 1180.669722812048,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011137170000097285,
"count": 1,
"is_parallel": true,
"self": 0.0002827050000178133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008310119999919152,
"count": 2,
"is_parallel": true,
"self": 0.0008310119999919152
}
}
},
"UnityEnvironment.step": {
"total": 0.03163247200001251,
"count": 1,
"is_parallel": true,
"self": 0.0003313089999892327,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024904200000719356,
"count": 1,
"is_parallel": true,
"self": 0.00024904200000719356
},
"communicator.exchange": {
"total": 0.030335623000041778,
"count": 1,
"is_parallel": true,
"self": 0.030335623000041778
},
"steps_from_proto": {
"total": 0.0007164979999743082,
"count": 1,
"is_parallel": true,
"self": 0.00019109599998046178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005254019999938464,
"count": 2,
"is_parallel": true,
"self": 0.0005254019999938464
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1240.3539985699604,
"count": 231092,
"is_parallel": true,
"self": 36.63969658576525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.20552486512463,
"count": 231092,
"is_parallel": true,
"self": 80.20552486512463
},
"communicator.exchange": {
"total": 1036.75974793007,
"count": 231092,
"is_parallel": true,
"self": 1036.75974793007
},
"steps_from_proto": {
"total": 86.74902918900045,
"count": 231092,
"is_parallel": true,
"self": 31.712972617181208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.036056571819245,
"count": 462184,
"is_parallel": true,
"self": 55.036056571819245
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 473.2632530399351,
"count": 231093,
"self": 6.671164812907762,
"children": {
"process_trajectory": {
"total": 152.87736040102618,
"count": 231093,
"self": 151.6297116790264,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2476487219997807,
"count": 10,
"self": 1.2476487219997807
}
}
},
"_update_policy": {
"total": 313.71472782600114,
"count": 97,
"self": 249.2658866450077,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.44884118099344,
"count": 2910,
"self": 64.44884118099344
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.389996193931438e-07,
"count": 1,
"self": 9.389996193931438e-07
},
"TrainerController._save_models": {
"total": 0.11436156400031905,
"count": 1,
"self": 0.0017849000005298876,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11257666399978916,
"count": 1,
"self": 0.11257666399978916
}
}
}
}
}
}
}