ppo-Huggy / run_logs /timers.json
sErial03's picture
[ADD]:Upload Huggy model
82c5802 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066898822784424,
"min": 1.4066898822784424,
"max": 1.4289195537567139,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70403.421875,
"min": 69003.125,
"max": 78152.9765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.4585448392555,
"min": 80.9673202614379,
"max": 403.336,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49324.0,
"min": 48920.0,
"max": 50417.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999872.0,
"min": 49852.0,
"max": 1999872.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999872.0,
"min": 49852.0,
"max": 1999872.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.441666841506958,
"min": 0.02898247167468071,
"max": 2.441666841506958,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1443.025146484375,
"min": 3.5938265323638916,
"max": 1467.0601806640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.826168850392053,
"min": 1.8123789545028441,
"max": 3.9119144344671826,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2261.265790581703,
"min": 224.73499035835266,
"max": 2317.308820784092,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.826168850392053,
"min": 1.8123789545028441,
"max": 3.9119144344671826,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2261.265790581703,
"min": 224.73499035835266,
"max": 2317.308820784092,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017832873197686342,
"min": 0.012901500280551974,
"max": 0.019348607320959367,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05349861959305902,
"min": 0.027001030100897577,
"max": 0.056782040259956076,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055904522248440315,
"min": 0.02517776054640611,
"max": 0.05734415737291177,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16771356674532095,
"min": 0.05035552109281222,
"max": 0.17203247211873532,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3097488967833197e-06,
"min": 3.3097488967833197e-06,
"max": 0.00029537130154289997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.929246690349959e-06,
"min": 9.929246690349959e-06,
"max": 0.0008441241186252998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110321666666665,
"min": 0.10110321666666665,
"max": 0.19845710000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30330964999999993,
"min": 0.20733605,
"max": 0.5813747000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.505051166666646e-05,
"min": 6.505051166666646e-05,
"max": 0.0049230092900000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019515153499999937,
"min": 0.00019515153499999937,
"max": 0.014070597530000003,
"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": "1735548396",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735552843"
},
"total": 4447.138706041001,
"count": 1,
"self": 0.6425014190008369,
"children": {
"run_training.setup": {
"total": 0.0759429669999463,
"count": 1,
"self": 0.0759429669999463
},
"TrainerController.start_learning": {
"total": 4446.420261655,
"count": 1,
"self": 8.014627233105784,
"children": {
"TrainerController._reset_env": {
"total": 9.731506801999899,
"count": 1,
"self": 9.731506801999899
},
"TrainerController.advance": {
"total": 4428.565895193895,
"count": 232284,
"self": 8.038229065676205,
"children": {
"env_step": {
"total": 2727.8093445611253,
"count": 232284,
"self": 2252.5325150141716,
"children": {
"SubprocessEnvManager._take_step": {
"total": 470.0036189979779,
"count": 232284,
"self": 29.258904630888537,
"children": {
"TorchPolicy.evaluate": {
"total": 440.7447143670894,
"count": 222944,
"self": 440.7447143670894
}
}
},
"workers": {
"total": 5.273210548975499,
"count": 232284,
"self": 0.0,
"children": {
"worker_root": {
"total": 4434.938269853106,
"count": 232284,
"is_parallel": true,
"self": 2634.7448360962467,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009571240000241232,
"count": 1,
"is_parallel": true,
"self": 0.00026314299998375645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006939810000403668,
"count": 2,
"is_parallel": true,
"self": 0.0006939810000403668
}
}
},
"UnityEnvironment.step": {
"total": 0.06601356299995587,
"count": 1,
"is_parallel": true,
"self": 0.0006916220000903195,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030317199991714006,
"count": 1,
"is_parallel": true,
"self": 0.00030317199991714006
},
"communicator.exchange": {
"total": 0.06370706799998516,
"count": 1,
"is_parallel": true,
"self": 0.06370706799998516
},
"steps_from_proto": {
"total": 0.00131170099996325,
"count": 1,
"is_parallel": true,
"self": 0.00030144499999096297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001010255999972287,
"count": 2,
"is_parallel": true,
"self": 0.001010255999972287
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1800.1934337568596,
"count": 232283,
"is_parallel": true,
"self": 55.422078601704015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 104.92655847106266,
"count": 232283,
"is_parallel": true,
"self": 104.92655847106266
},
"communicator.exchange": {
"total": 1511.0025026140427,
"count": 232283,
"is_parallel": true,
"self": 1511.0025026140427
},
"steps_from_proto": {
"total": 128.84229407005023,
"count": 232283,
"is_parallel": true,
"self": 42.178307701701556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 86.66398636834867,
"count": 464566,
"is_parallel": true,
"self": 86.66398636834867
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1692.7183215670939,
"count": 232284,
"self": 12.173095381008807,
"children": {
"process_trajectory": {
"total": 262.41896275708484,
"count": 232284,
"self": 261.23893841508436,
"children": {
"RLTrainer._checkpoint": {
"total": 1.180024342000479,
"count": 10,
"self": 1.180024342000479
}
}
},
"_update_policy": {
"total": 1418.1262634290003,
"count": 97,
"self": 342.7026578840009,
"children": {
"TorchPPOOptimizer.update": {
"total": 1075.4236055449994,
"count": 2910,
"self": 1075.4236055449994
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1849997463286854e-06,
"count": 1,
"self": 1.1849997463286854e-06
},
"TrainerController._save_models": {
"total": 0.1082312409998849,
"count": 1,
"self": 0.0027208689998587943,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10551037200002611,
"count": 1,
"self": 0.10551037200002611
}
}
}
}
}
}
}