ppo-Huggy / run_logs /timers.json
inventwithdean's picture
Huggy v0
cd5642a verified
raw
history blame contribute delete
No virus
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4099323749542236,
"min": 1.4099323749542236,
"max": 1.4292129278182983,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70465.6015625,
"min": 68761.2109375,
"max": 78220.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 106.57815845824412,
"min": 79.27608346709471,
"max": 388.9922480620155,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49772.0,
"min": 48842.0,
"max": 50180.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999685.0,
"min": 49559.0,
"max": 1999685.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999685.0,
"min": 49559.0,
"max": 1999685.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3646159172058105,
"min": 0.16908565163612366,
"max": 2.5027546882629395,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1104.275634765625,
"min": 21.642963409423828,
"max": 1534.2764892578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.508184065783049,
"min": 1.740510475821793,
"max": 4.06889255579353,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1638.321958720684,
"min": 222.7853409051895,
"max": 2451.994974732399,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.508184065783049,
"min": 1.740510475821793,
"max": 4.06889255579353,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1638.321958720684,
"min": 222.7853409051895,
"max": 2451.994974732399,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017148488525279188,
"min": 0.012953496576099295,
"max": 0.0188888559564172,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05144546557583757,
"min": 0.027860676694156913,
"max": 0.056653323959714424,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048627642914652824,
"min": 0.020235149438182512,
"max": 0.06401841708769401,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14588292874395847,
"min": 0.040470298876365024,
"max": 0.17957337213059266,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.301048899683335e-06,
"min": 3.301048899683335e-06,
"max": 0.00029532360155879996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.903146699050004e-06,
"min": 9.903146699050004e-06,
"max": 0.0008438938687020498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110031666666668,
"min": 0.10110031666666668,
"max": 0.19844119999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30330095,
"min": 0.20743480000000003,
"max": 0.5812979500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.490580166666671e-05,
"min": 6.490580166666671e-05,
"max": 0.004922215880000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019471740500000016,
"min": 0.00019471740500000016,
"max": 0.014066767705000002,
"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": "1717871660",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717874127"
},
"total": 2467.1859702919996,
"count": 1,
"self": 0.9024579649999396,
"children": {
"run_training.setup": {
"total": 0.05731574700001829,
"count": 1,
"self": 0.05731574700001829
},
"TrainerController.start_learning": {
"total": 2466.22619658,
"count": 1,
"self": 4.513253234962576,
"children": {
"TrainerController._reset_env": {
"total": 3.2170997239999792,
"count": 1,
"self": 3.2170997239999792
},
"TrainerController.advance": {
"total": 2458.3203436150375,
"count": 232254,
"self": 4.677470596011972,
"children": {
"env_step": {
"total": 1947.4997554789986,
"count": 232254,
"self": 1610.7824727869297,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.83700998903737,
"count": 232254,
"self": 16.474374835026197,
"children": {
"TorchPolicy.evaluate": {
"total": 317.3626351540112,
"count": 223062,
"self": 317.3626351540112
}
}
},
"workers": {
"total": 2.8802727030316078,
"count": 232254,
"self": 0.0,
"children": {
"worker_root": {
"total": 2458.908264199999,
"count": 232254,
"is_parallel": true,
"self": 1161.4968691510924,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009303710000381216,
"count": 1,
"is_parallel": true,
"self": 0.00025078900006292315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006795819999751984,
"count": 2,
"is_parallel": true,
"self": 0.0006795819999751984
}
}
},
"UnityEnvironment.step": {
"total": 0.031158795000010286,
"count": 1,
"is_parallel": true,
"self": 0.0004092179999588552,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021067900001980888,
"count": 1,
"is_parallel": true,
"self": 0.00021067900001980888
},
"communicator.exchange": {
"total": 0.02973556599999938,
"count": 1,
"is_parallel": true,
"self": 0.02973556599999938
},
"steps_from_proto": {
"total": 0.0008033320000322419,
"count": 1,
"is_parallel": true,
"self": 0.0002114600000027167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005918720000295252,
"count": 2,
"is_parallel": true,
"self": 0.0005918720000295252
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1297.4113950489066,
"count": 232253,
"is_parallel": true,
"self": 39.04324303785643,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.8764548500211,
"count": 232253,
"is_parallel": true,
"self": 81.8764548500211
},
"communicator.exchange": {
"total": 1085.5442322429508,
"count": 232253,
"is_parallel": true,
"self": 1085.5442322429508
},
"steps_from_proto": {
"total": 90.94746491807808,
"count": 232253,
"is_parallel": true,
"self": 32.353186955133594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.59427796294449,
"count": 464506,
"is_parallel": true,
"self": 58.59427796294449
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 506.1431175400268,
"count": 232254,
"self": 6.820673124952975,
"children": {
"process_trajectory": {
"total": 155.55651035407698,
"count": 232254,
"self": 154.12471583107668,
"children": {
"RLTrainer._checkpoint": {
"total": 1.431794523000292,
"count": 10,
"self": 1.431794523000292
}
}
},
"_update_policy": {
"total": 343.76593406099687,
"count": 97,
"self": 279.0288975690018,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.73703649199507,
"count": 2910,
"self": 64.73703649199507
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.535999672341859e-06,
"count": 1,
"self": 1.535999672341859e-06
},
"TrainerController._save_models": {
"total": 0.17549847000009322,
"count": 1,
"self": 0.002983672000027582,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17251479800006564,
"count": 1,
"self": 0.17251479800006564
}
}
}
}
}
}
}