ppo-Huggy-v2 / run_logs /timers.json
rlap28's picture
Huggy-v2
b2e8b68 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4027467966079712,
"min": 1.4027467966079712,
"max": 1.4290913343429565,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71603.2109375,
"min": 68797.515625,
"max": 76295.21875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.33471933471934,
"min": 100.46450304259635,
"max": 384.12213740458014,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49704.0,
"min": 49003.0,
"max": 50320.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999548.0,
"min": 49998.0,
"max": 1999548.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999548.0,
"min": 49998.0,
"max": 1999548.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.327334403991699,
"min": 0.057792481034994125,
"max": 2.3649470806121826,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1119.4478759765625,
"min": 7.513022422790527,
"max": 1141.986083984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6606519244564795,
"min": 1.7914608563368137,
"max": 3.7737253029709277,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1760.7735756635666,
"min": 232.88991132378578,
"max": 1760.7735756635666,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6606519244564795,
"min": 1.7914608563368137,
"max": 3.7737253029709277,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1760.7735756635666,
"min": 232.88991132378578,
"max": 1760.7735756635666,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01578992176776713,
"min": 0.011955371889376289,
"max": 0.019784041512563515,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03157984353553426,
"min": 0.029095470350390923,
"max": 0.0587616033454348,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048213582920531434,
"min": 0.023157543782144782,
"max": 0.05703711907068889,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09642716584106287,
"min": 0.046315087564289564,
"max": 0.17111135721206666,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.359998546699988e-06,
"min": 4.359998546699988e-06,
"max": 0.0002953293765568751,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.719997093399976e-06,
"min": 8.719997093399976e-06,
"max": 0.0008435989688003498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1014533,
"min": 0.1014533,
"max": 0.19844312500000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2029066,
"min": 0.2029066,
"max": 0.58119965,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.251966999999982e-05,
"min": 8.251966999999982e-05,
"max": 0.0049223119375,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016503933999999963,
"min": 0.00016503933999999963,
"max": 0.014061862535,
"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": "1723639256",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723641670"
},
"total": 2414.507351092,
"count": 1,
"self": 0.6699460649997491,
"children": {
"run_training.setup": {
"total": 0.059994386000028044,
"count": 1,
"self": 0.059994386000028044
},
"TrainerController.start_learning": {
"total": 2413.777410641,
"count": 1,
"self": 4.288510414047778,
"children": {
"TrainerController._reset_env": {
"total": 3.513083678999976,
"count": 1,
"self": 3.513083678999976
},
"TrainerController.advance": {
"total": 2405.776579035952,
"count": 231021,
"self": 4.5609921398877304,
"children": {
"env_step": {
"total": 1915.4580238600015,
"count": 231021,
"self": 1577.2578094040712,
"children": {
"SubprocessEnvManager._take_step": {
"total": 335.31093218393113,
"count": 231021,
"self": 17.181028025898115,
"children": {
"TorchPolicy.evaluate": {
"total": 318.129904158033,
"count": 222985,
"self": 318.129904158033
}
}
},
"workers": {
"total": 2.88928227199915,
"count": 231021,
"self": 0.0,
"children": {
"worker_root": {
"total": 2406.441698376958,
"count": 231021,
"is_parallel": true,
"self": 1134.3391732809896,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009033150000163914,
"count": 1,
"is_parallel": true,
"self": 0.00023182900002893803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006714859999874534,
"count": 2,
"is_parallel": true,
"self": 0.0006714859999874534
}
}
},
"UnityEnvironment.step": {
"total": 0.030935425999985,
"count": 1,
"is_parallel": true,
"self": 0.0003799510000135342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002014799999869865,
"count": 1,
"is_parallel": true,
"self": 0.0002014799999869865
},
"communicator.exchange": {
"total": 0.029549663000011606,
"count": 1,
"is_parallel": true,
"self": 0.029549663000011606
},
"steps_from_proto": {
"total": 0.0008043319999728737,
"count": 1,
"is_parallel": true,
"self": 0.0002377369999635448,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005665950000093289,
"count": 2,
"is_parallel": true,
"self": 0.0005665950000093289
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.1025250959683,
"count": 231020,
"is_parallel": true,
"self": 38.452517033832464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.55724969617751,
"count": 231020,
"is_parallel": true,
"self": 81.55724969617751
},
"communicator.exchange": {
"total": 1060.157203378022,
"count": 231020,
"is_parallel": true,
"self": 1060.157203378022
},
"steps_from_proto": {
"total": 91.93555498793637,
"count": 231020,
"is_parallel": true,
"self": 34.687646684875574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.2479083030608,
"count": 462040,
"is_parallel": true,
"self": 57.2479083030608
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 485.7575630360632,
"count": 231021,
"self": 7.088581421052652,
"children": {
"process_trajectory": {
"total": 151.6692461870113,
"count": 231021,
"self": 150.2410822580119,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4281639289994246,
"count": 10,
"self": 1.4281639289994246
}
}
},
"_update_policy": {
"total": 326.9997354279992,
"count": 96,
"self": 263.4240162310005,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.575719196998705,
"count": 2880,
"self": 63.575719196998705
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4390002434083726e-06,
"count": 1,
"self": 1.4390002434083726e-06
},
"TrainerController._save_models": {
"total": 0.19923607300006552,
"count": 1,
"self": 0.0027945309998358425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19644154200022967,
"count": 1,
"self": 0.19644154200022967
}
}
}
}
}
}
}