ppo-Huggy / run_logs /timers.json
DivyaMathi's picture
Huggy
6b535db verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.399869441986084,
"min": 1.399869441986084,
"max": 1.42750084400177,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70066.265625,
"min": 68955.8203125,
"max": 77314.140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.66067864271457,
"min": 79.32263242375602,
"max": 397.6507936507937,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49429.0,
"min": 48726.0,
"max": 50152.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999983.0,
"min": 49832.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999983.0,
"min": 49832.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.428809404373169,
"min": 0.10263291001319885,
"max": 2.5413811206817627,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1216.83349609375,
"min": 12.829113960266113,
"max": 1501.3372802734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.714715164102718,
"min": 1.908950879096985,
"max": 4.041533569459213,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1861.0722972154617,
"min": 238.6188598871231,
"max": 2374.855134308338,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.714715164102718,
"min": 1.908950879096985,
"max": 4.041533569459213,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1861.0722972154617,
"min": 238.6188598871231,
"max": 2374.855134308338,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017388613568699737,
"min": 0.013010124194746217,
"max": 0.020111817697761582,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05216584070609921,
"min": 0.026020248389492434,
"max": 0.05856237032227606,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04824957744114929,
"min": 0.022445220531274873,
"max": 0.06289754882454872,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14474873232344787,
"min": 0.044890441062549746,
"max": 0.1755585350096226,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.254048915350006e-06,
"min": 3.254048915350006e-06,
"max": 0.00029530822656392494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.762146746050018e-06,
"min": 9.762146746050018e-06,
"max": 0.0008442157685947499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108464999999998,
"min": 0.10108464999999998,
"max": 0.198436075,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30325394999999994,
"min": 0.2073505,
"max": 0.5814052500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.412403500000009e-05,
"min": 6.412403500000009e-05,
"max": 0.0049219601425,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019237210500000027,
"min": 0.00019237210500000027,
"max": 0.014072121974999997,
"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": "1710249185",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1710251791"
},
"total": 2606.7224861110003,
"count": 1,
"self": 0.43994210800019573,
"children": {
"run_training.setup": {
"total": 0.060648560999993606,
"count": 1,
"self": 0.060648560999993606
},
"TrainerController.start_learning": {
"total": 2606.221895442,
"count": 1,
"self": 4.862650945162386,
"children": {
"TrainerController._reset_env": {
"total": 2.8286172410000177,
"count": 1,
"self": 2.8286172410000177
},
"TrainerController.advance": {
"total": 2598.3937466638376,
"count": 232231,
"self": 5.14805260697085,
"children": {
"env_step": {
"total": 2104.300091247949,
"count": 232231,
"self": 1736.3100917209103,
"children": {
"SubprocessEnvManager._take_step": {
"total": 364.71986672096443,
"count": 232231,
"self": 18.778028565903185,
"children": {
"TorchPolicy.evaluate": {
"total": 345.94183815506125,
"count": 223009,
"self": 345.94183815506125
}
}
},
"workers": {
"total": 3.270132806074116,
"count": 232231,
"self": 0.0,
"children": {
"worker_root": {
"total": 2598.354691012965,
"count": 232231,
"is_parallel": true,
"self": 1201.838550635005,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010203429999933178,
"count": 1,
"is_parallel": true,
"self": 0.00021787399998629553,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008024690000070223,
"count": 2,
"is_parallel": true,
"self": 0.0008024690000070223
}
}
},
"UnityEnvironment.step": {
"total": 0.03557546099995079,
"count": 1,
"is_parallel": true,
"self": 0.0004026559998351331,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019888000002765693,
"count": 1,
"is_parallel": true,
"self": 0.00019888000002765693
},
"communicator.exchange": {
"total": 0.03404675200005158,
"count": 1,
"is_parallel": true,
"self": 0.03404675200005158
},
"steps_from_proto": {
"total": 0.0009271730000364187,
"count": 1,
"is_parallel": true,
"self": 0.0002603849999900376,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006667880000463811,
"count": 2,
"is_parallel": true,
"self": 0.0006667880000463811
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1396.5161403779598,
"count": 232230,
"is_parallel": true,
"self": 41.571657266037164,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.61344885200998,
"count": 232230,
"is_parallel": true,
"self": 90.61344885200998
},
"communicator.exchange": {
"total": 1164.7046997699588,
"count": 232230,
"is_parallel": true,
"self": 1164.7046997699588
},
"steps_from_proto": {
"total": 99.62633448995393,
"count": 232230,
"is_parallel": true,
"self": 37.91892466089945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.707409829054484,
"count": 464460,
"is_parallel": true,
"self": 61.707409829054484
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 488.94560280891795,
"count": 232231,
"self": 7.588095030973818,
"children": {
"process_trajectory": {
"total": 165.19369593794437,
"count": 232231,
"self": 163.86515051694408,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3285454210002854,
"count": 10,
"self": 1.3285454210002854
}
}
},
"_update_policy": {
"total": 316.16381183999977,
"count": 97,
"self": 251.42274862899694,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.74106321100282,
"count": 2910,
"self": 64.74106321100282
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.244000031874748e-06,
"count": 1,
"self": 1.244000031874748e-06
},
"TrainerController._save_models": {
"total": 0.13687934800009316,
"count": 1,
"self": 0.0022511860001941386,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13462816199989902,
"count": 1,
"self": 0.13462816199989902
}
}
}
}
}
}
}