ppo-Huggy / run_logs /timers.json
polyconnect's picture
Huggy
59b5fb7 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070405960083008,
"min": 1.4070405960083008,
"max": 1.4267559051513672,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69483.8828125,
"min": 69026.125,
"max": 75953.53125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.312625250501,
"min": 83.49662162162163,
"max": 354.3191489361702,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49557.0,
"min": 48777.0,
"max": 50138.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49605.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49605.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3564302921295166,
"min": 0.07313764840364456,
"max": 2.515875816345215,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1175.8587646484375,
"min": 10.23927116394043,
"max": 1439.7994384765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5939222006855127,
"min": 1.76886364285435,
"max": 3.928199657691195,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1793.3671781420708,
"min": 247.640909999609,
"max": 2305.8531990647316,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5939222006855127,
"min": 1.76886364285435,
"max": 3.928199657691195,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1793.3671781420708,
"min": 247.640909999609,
"max": 2305.8531990647316,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.02038321700011794,
"min": 0.01466844069509534,
"max": 0.02045447578275343,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06114965100035382,
"min": 0.02933688139019068,
"max": 0.06114965100035382,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0512974739074707,
"min": 0.023522811693449816,
"max": 0.059926063567399976,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1538924217224121,
"min": 0.04704562338689963,
"max": 0.17050334339340528,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.329248890283337e-06,
"min": 3.329248890283337e-06,
"max": 0.000295271776576075,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.987746670850011e-06,
"min": 9.987746670850011e-06,
"max": 0.0008436411187862998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110971666666664,
"min": 0.10110971666666664,
"max": 0.19842392500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30332914999999994,
"min": 0.20736974999999996,
"max": 0.5812137,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.537486166666672e-05,
"min": 6.537486166666672e-05,
"max": 0.0049213538575,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019612458500000015,
"min": 0.00019612458500000015,
"max": 0.01406256363,
"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": "1716131381",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716135852"
},
"total": 4470.911713631999,
"count": 1,
"self": 1.2330788869994649,
"children": {
"run_training.setup": {
"total": 0.10144725100008145,
"count": 1,
"self": 0.10144725100008145
},
"TrainerController.start_learning": {
"total": 4469.577187494,
"count": 1,
"self": 8.37623679481294,
"children": {
"TrainerController._reset_env": {
"total": 4.014120017000096,
"count": 1,
"self": 4.014120017000096
},
"TrainerController.advance": {
"total": 4456.978390603186,
"count": 232396,
"self": 8.169716649387738,
"children": {
"env_step": {
"total": 2936.2182148918673,
"count": 232396,
"self": 2467.0637357410296,
"children": {
"SubprocessEnvManager._take_step": {
"total": 463.825665736927,
"count": 232396,
"self": 32.839570991786104,
"children": {
"TorchPolicy.evaluate": {
"total": 430.9860947451409,
"count": 223065,
"self": 430.9860947451409
}
}
},
"workers": {
"total": 5.32881341391078,
"count": 232396,
"self": 0.0,
"children": {
"worker_root": {
"total": 4454.858806254163,
"count": 232396,
"is_parallel": true,
"self": 2505.844078539125,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011605979999558258,
"count": 1,
"is_parallel": true,
"self": 0.0003218229999220057,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008387750000338201,
"count": 2,
"is_parallel": true,
"self": 0.0008387750000338201
}
}
},
"UnityEnvironment.step": {
"total": 0.03924627999992936,
"count": 1,
"is_parallel": true,
"self": 0.0004884650001031332,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002359489999435027,
"count": 1,
"is_parallel": true,
"self": 0.0002359489999435027
},
"communicator.exchange": {
"total": 0.037519003999932465,
"count": 1,
"is_parallel": true,
"self": 0.037519003999932465
},
"steps_from_proto": {
"total": 0.0010028619999502553,
"count": 1,
"is_parallel": true,
"self": 0.00028075300008367776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007221089998665775,
"count": 2,
"is_parallel": true,
"self": 0.0007221089998665775
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1949.0147277150381,
"count": 232395,
"is_parallel": true,
"self": 61.24941290789093,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 96.72479284106385,
"count": 232395,
"is_parallel": true,
"self": 96.72479284106385
},
"communicator.exchange": {
"total": 1652.9822117229278,
"count": 232395,
"is_parallel": true,
"self": 1652.9822117229278
},
"steps_from_proto": {
"total": 138.05831024315557,
"count": 232395,
"is_parallel": true,
"self": 43.946351742046545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 94.11195850110903,
"count": 464790,
"is_parallel": true,
"self": 94.11195850110903
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1512.5904590619314,
"count": 232396,
"self": 12.77638590291349,
"children": {
"process_trajectory": {
"total": 248.3786688320189,
"count": 232396,
"self": 246.8017167860197,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5769520459991782,
"count": 10,
"self": 1.5769520459991782
}
}
},
"_update_policy": {
"total": 1251.4354043269989,
"count": 97,
"self": 334.23336021199964,
"children": {
"TorchPPOOptimizer.update": {
"total": 917.2020441149992,
"count": 2910,
"self": 917.2020441149992
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7120000848080963e-06,
"count": 1,
"self": 1.7120000848080963e-06
},
"TrainerController._save_models": {
"total": 0.208438367000781,
"count": 1,
"self": 0.0058710130006147665,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20256735400016623,
"count": 1,
"self": 0.20256735400016623
}
}
}
}
}
}
}