ppo-Huggy / run_logs /timers.json
Logic-TARS's picture
Huggy
5cf058a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4069340229034424,
"min": 1.4069340229034424,
"max": 1.4294182062149048,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69965.421875,
"min": 69240.7265625,
"max": 76695.3359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.35838150289017,
"min": 88.98561151079137,
"max": 390.5546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50010.0,
"min": 48975.0,
"max": 50309.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999826.0,
"min": 49988.0,
"max": 1999826.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999826.0,
"min": 49988.0,
"max": 1999826.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4667673110961914,
"min": 0.11266784369945526,
"max": 2.4667673110961914,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1280.252197265625,
"min": 14.308815956115723,
"max": 1317.6549072265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9250181021028863,
"min": 1.8226899253571127,
"max": 3.9250181021028863,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2037.0843949913979,
"min": 231.48162052035332,
"max": 2084.0359370708466,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9250181021028863,
"min": 1.8226899253571127,
"max": 3.9250181021028863,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2037.0843949913979,
"min": 231.48162052035332,
"max": 2084.0359370708466,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017206923363285873,
"min": 0.013594712619669734,
"max": 0.021319861147397506,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.034413846726571745,
"min": 0.027189425239339468,
"max": 0.059468482482770924,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054899633613725504,
"min": 0.02246641175200542,
"max": 0.06692706358929475,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10979926722745101,
"min": 0.04493282350401084,
"max": 0.20078119076788425,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.635398454899997e-06,
"min": 4.635398454899997e-06,
"max": 0.000295303426565525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.270796909799995e-06,
"min": 9.270796909799995e-06,
"max": 0.0008441035686321502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10154510000000001,
"min": 0.10154510000000001,
"max": 0.198434475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20309020000000003,
"min": 0.20309020000000003,
"max": 0.5813678499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.710048999999996e-05,
"min": 8.710048999999996e-05,
"max": 0.004921880302500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001742009799999999,
"min": 0.0001742009799999999,
"max": 0.014070255715,
"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": "1743832538",
"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": "1743835057"
},
"total": 2518.678623332,
"count": 1,
"self": 0.7415078769995489,
"children": {
"run_training.setup": {
"total": 0.023314004999974713,
"count": 1,
"self": 0.023314004999974713
},
"TrainerController.start_learning": {
"total": 2517.9138014500004,
"count": 1,
"self": 4.488141123982587,
"children": {
"TrainerController._reset_env": {
"total": 2.986419381000019,
"count": 1,
"self": 2.986419381000019
},
"TrainerController.advance": {
"total": 2510.271286572018,
"count": 231663,
"self": 4.463177037111109,
"children": {
"env_step": {
"total": 1972.9358138609077,
"count": 231663,
"self": 1546.1753182748541,
"children": {
"SubprocessEnvManager._take_step": {
"total": 424.03108996211085,
"count": 231663,
"self": 15.991306465128446,
"children": {
"TorchPolicy.evaluate": {
"total": 408.0397834969824,
"count": 222896,
"self": 408.0397834969824
}
}
},
"workers": {
"total": 2.729405623942739,
"count": 231663,
"self": 0.0,
"children": {
"worker_root": {
"total": 2510.172100129951,
"count": 231663,
"is_parallel": true,
"self": 1248.805822299916,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011074190000499584,
"count": 1,
"is_parallel": true,
"self": 0.00040033600021160964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007070829998383488,
"count": 2,
"is_parallel": true,
"self": 0.0007070829998383488
}
}
},
"UnityEnvironment.step": {
"total": 0.030244594000009783,
"count": 1,
"is_parallel": true,
"self": 0.0003304260000049908,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000217471000041769,
"count": 1,
"is_parallel": true,
"self": 0.000217471000041769
},
"communicator.exchange": {
"total": 0.02895717599994896,
"count": 1,
"is_parallel": true,
"self": 0.02895717599994896
},
"steps_from_proto": {
"total": 0.0007395210000140651,
"count": 1,
"is_parallel": true,
"self": 0.00019986700010576897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005396539999082961,
"count": 2,
"is_parallel": true,
"self": 0.0005396539999082961
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.3662778300352,
"count": 231662,
"is_parallel": true,
"self": 37.42363250576841,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.40244011515438,
"count": 231662,
"is_parallel": true,
"self": 82.40244011515438
},
"communicator.exchange": {
"total": 1052.4264552331504,
"count": 231662,
"is_parallel": true,
"self": 1052.4264552331504
},
"steps_from_proto": {
"total": 89.11374997596215,
"count": 231662,
"is_parallel": true,
"self": 33.040167772044924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.073582203917226,
"count": 463324,
"is_parallel": true,
"self": 56.073582203917226
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 532.8722956739992,
"count": 231663,
"self": 6.8638564161210525,
"children": {
"process_trajectory": {
"total": 163.55855389387818,
"count": 231663,
"self": 162.2163311628791,
"children": {
"RLTrainer._checkpoint": {
"total": 1.342222730999083,
"count": 10,
"self": 1.342222730999083
}
}
},
"_update_policy": {
"total": 362.449885364,
"count": 96,
"self": 294.45825516100024,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.99163020299977,
"count": 2880,
"self": 67.99163020299977
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1859997357532848e-06,
"count": 1,
"self": 1.1859997357532848e-06
},
"TrainerController._save_models": {
"total": 0.16795318699996642,
"count": 1,
"self": 0.002715037999678316,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1652381490002881,
"count": 1,
"self": 0.1652381490002881
}
}
}
}
}
}
}