ppo-Huggy / run_logs /timers.json
Jarles's picture
Huggy
8e14687 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4028037786483765,
"min": 1.4028037786483765,
"max": 1.426377296447754,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70001.3125,
"min": 68664.96875,
"max": 75830.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.21478873239437,
"min": 86.2303664921466,
"max": 409.57377049180326,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49538.0,
"min": 49013.0,
"max": 49985.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999983.0,
"min": 49628.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999983.0,
"min": 49628.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.427039384841919,
"min": 0.10219750553369522,
"max": 2.4746687412261963,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1380.9854736328125,
"min": 12.365898132324219,
"max": 1380.9854736328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.760965992151539,
"min": 1.798029024862061,
"max": 3.939282929446517,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2139.9896495342255,
"min": 217.56151200830936,
"max": 2181.8874891996384,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.760965992151539,
"min": 1.798029024862061,
"max": 3.939282929446517,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2139.9896495342255,
"min": 217.56151200830936,
"max": 2181.8874891996384,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01889296558802016,
"min": 0.013666585526920648,
"max": 0.01889296558802016,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03778593117604032,
"min": 0.027465943136485295,
"max": 0.054549122628426025,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05249760523438454,
"min": 0.0220302759980162,
"max": 0.060145708877179356,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10499521046876908,
"min": 0.0440605519960324,
"max": 0.18043712663153808,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.5576984807999955e-06,
"min": 4.5576984807999955e-06,
"max": 0.00029532615155795005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.115396961599991e-06,
"min": 9.115396961599991e-06,
"max": 0.00084378046873985,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1015192,
"min": 0.1015192,
"max": 0.19844205000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2030384,
"min": 0.2030384,
"max": 0.5812601500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.580807999999994e-05,
"min": 8.580807999999994e-05,
"max": 0.004922258294999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017161615999999988,
"min": 0.00017161615999999988,
"max": 0.014064881485000003,
"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": "1707175772",
"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=Huggy --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707178044"
},
"total": 2271.5697254059996,
"count": 1,
"self": 0.4339040219988419,
"children": {
"run_training.setup": {
"total": 0.04612291900002674,
"count": 1,
"self": 0.04612291900002674
},
"TrainerController.start_learning": {
"total": 2271.0896984650008,
"count": 1,
"self": 4.389327079996292,
"children": {
"TrainerController._reset_env": {
"total": 3.046146332000035,
"count": 1,
"self": 3.046146332000035
},
"TrainerController.advance": {
"total": 2263.5413942240043,
"count": 232157,
"self": 4.3534001100047135,
"children": {
"env_step": {
"total": 1798.1009313240925,
"count": 232157,
"self": 1480.7261327500585,
"children": {
"SubprocessEnvManager._take_step": {
"total": 314.7134376300796,
"count": 232157,
"self": 16.114601621143493,
"children": {
"TorchPolicy.evaluate": {
"total": 298.59883600893613,
"count": 222975,
"self": 298.59883600893613
}
}
},
"workers": {
"total": 2.661360943954378,
"count": 232157,
"self": 0.0,
"children": {
"worker_root": {
"total": 2263.748434427074,
"count": 232157,
"is_parallel": true,
"self": 1056.2130519371058,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010068389999560168,
"count": 1,
"is_parallel": true,
"self": 0.0002685360000214132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007383029999346036,
"count": 2,
"is_parallel": true,
"self": 0.0007383029999346036
}
}
},
"UnityEnvironment.step": {
"total": 0.03319710899995698,
"count": 1,
"is_parallel": true,
"self": 0.0002963769998132193,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022039500004211732,
"count": 1,
"is_parallel": true,
"self": 0.00022039500004211732
},
"communicator.exchange": {
"total": 0.031937278999976115,
"count": 1,
"is_parallel": true,
"self": 0.031937278999976115
},
"steps_from_proto": {
"total": 0.0007430580001255294,
"count": 1,
"is_parallel": true,
"self": 0.00021238400017864478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005306739999468846,
"count": 2,
"is_parallel": true,
"self": 0.0005306739999468846
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1207.535382489968,
"count": 232156,
"is_parallel": true,
"self": 39.22669852307831,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.8504733959262,
"count": 232156,
"is_parallel": true,
"self": 79.8504733959262
},
"communicator.exchange": {
"total": 1001.8758292269067,
"count": 232156,
"is_parallel": true,
"self": 1001.8758292269067
},
"steps_from_proto": {
"total": 86.58238134405678,
"count": 232156,
"is_parallel": true,
"self": 30.399361320895423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.18302002316136,
"count": 464312,
"is_parallel": true,
"self": 56.18302002316136
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 461.0870627899069,
"count": 232157,
"self": 6.501791632932509,
"children": {
"process_trajectory": {
"total": 143.93332422497588,
"count": 232157,
"self": 142.63153802497618,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3017861999996967,
"count": 10,
"self": 1.3017861999996967
}
}
},
"_update_policy": {
"total": 310.6519469319985,
"count": 96,
"self": 248.95363763299497,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.69830929900354,
"count": 2880,
"self": 61.69830929900354
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.289998731925152e-07,
"count": 1,
"self": 8.289998731925152e-07
},
"TrainerController._save_models": {
"total": 0.11283000000003085,
"count": 1,
"self": 0.0020037870008309255,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11082621299919992,
"count": 1,
"self": 0.11082621299919992
}
}
}
}
}
}
}