ppo-Huggy / run_logs /timers.json
acadia611's picture
Huggy
57e5583 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042904376983643,
"min": 1.4042904376983643,
"max": 1.425531029701233,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71697.453125,
"min": 65209.64453125,
"max": 81052.421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.2707423580786,
"min": 103.89727463312369,
"max": 409.0813008130081,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49130.0,
"min": 48843.0,
"max": 50317.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999415.0,
"min": 49690.0,
"max": 1999415.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999415.0,
"min": 49690.0,
"max": 1999415.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.377159357070923,
"min": 0.06531991809606552,
"max": 2.377159357070923,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1088.739013671875,
"min": 7.969029903411865,
"max": 1088.739013671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7369398819567334,
"min": 1.6704631982768168,
"max": 3.839708349292661,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1711.518465936184,
"min": 203.79651018977165,
"max": 1711.518465936184,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7369398819567334,
"min": 1.6704631982768168,
"max": 3.839708349292661,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1711.518465936184,
"min": 203.79651018977165,
"max": 1711.518465936184,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01661640321908635,
"min": 0.013925336267372282,
"max": 0.020491606253199277,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0332328064381727,
"min": 0.027850672534744565,
"max": 0.05670826736216744,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.047624350028733414,
"min": 0.021765628891686598,
"max": 0.06431242016454537,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09524870005746683,
"min": 0.043531257783373196,
"max": 0.19293726049363613,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.40904853035e-06,
"min": 4.40904853035e-06,
"max": 0.000295310176563275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.8180970607e-06,
"min": 8.8180970607e-06,
"max": 0.0008440110186629999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10146964999999998,
"min": 0.10146964999999998,
"max": 0.19843672500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20293929999999996,
"min": 0.20293929999999996,
"max": 0.581337,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.3335535e-05,
"min": 8.3335535e-05,
"max": 0.004921992577499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016667107,
"min": 0.00016667107,
"max": 0.014068716299999999,
"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": "1739163549",
"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": "1739167591"
},
"total": 4041.7434665739997,
"count": 1,
"self": 0.544225789000393,
"children": {
"run_training.setup": {
"total": 0.029667225999901348,
"count": 1,
"self": 0.029667225999901348
},
"TrainerController.start_learning": {
"total": 4041.1695735589997,
"count": 1,
"self": 7.38082933010719,
"children": {
"TrainerController._reset_env": {
"total": 3.0522497590000057,
"count": 1,
"self": 3.0522497590000057
},
"TrainerController.advance": {
"total": 4030.631738480892,
"count": 230920,
"self": 7.24659297399694,
"children": {
"env_step": {
"total": 2589.762784463888,
"count": 230920,
"self": 2163.6299814959975,
"children": {
"SubprocessEnvManager._take_step": {
"total": 421.32858100894737,
"count": 230920,
"self": 25.356062720986756,
"children": {
"TorchPolicy.evaluate": {
"total": 395.9725182879606,
"count": 222988,
"self": 395.9725182879606
}
}
},
"workers": {
"total": 4.804221958942662,
"count": 230920,
"self": 0.0,
"children": {
"worker_root": {
"total": 4029.5394121199115,
"count": 230920,
"is_parallel": true,
"self": 2296.0590103208306,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011710300000231655,
"count": 1,
"is_parallel": true,
"self": 0.0002844719999757217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008865580000474438,
"count": 2,
"is_parallel": true,
"self": 0.0008865580000474438
}
}
},
"UnityEnvironment.step": {
"total": 0.034736461000079544,
"count": 1,
"is_parallel": true,
"self": 0.00039648600011332746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022590399998989596,
"count": 1,
"is_parallel": true,
"self": 0.00022590399998989596
},
"communicator.exchange": {
"total": 0.033311232999949425,
"count": 1,
"is_parallel": true,
"self": 0.033311232999949425
},
"steps_from_proto": {
"total": 0.0008028380000268953,
"count": 1,
"is_parallel": true,
"self": 0.00021552800001245487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005873100000144404,
"count": 2,
"is_parallel": true,
"self": 0.0005873100000144404
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1733.4804017990812,
"count": 230919,
"is_parallel": true,
"self": 54.11088279606906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 102.01945237386678,
"count": 230919,
"is_parallel": true,
"self": 102.01945237386678
},
"communicator.exchange": {
"total": 1453.3427299821133,
"count": 230919,
"is_parallel": true,
"self": 1453.3427299821133
},
"steps_from_proto": {
"total": 124.00733664703182,
"count": 230919,
"is_parallel": true,
"self": 39.6769673961079,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.33036925092392,
"count": 461838,
"is_parallel": true,
"self": 84.33036925092392
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1433.6223610430075,
"count": 230920,
"self": 11.185219043910593,
"children": {
"process_trajectory": {
"total": 222.84162778609357,
"count": 230920,
"self": 221.46318670609253,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3784410800010392,
"count": 10,
"self": 1.3784410800010392
}
}
},
"_update_policy": {
"total": 1199.5955142130033,
"count": 96,
"self": 313.07814792800707,
"children": {
"TorchPPOOptimizer.update": {
"total": 886.5173662849962,
"count": 2880,
"self": 886.5173662849962
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.73000169324223e-07,
"count": 1,
"self": 9.73000169324223e-07
},
"TrainerController._save_models": {
"total": 0.10475501600012649,
"count": 1,
"self": 0.0029933360001450637,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10176167999998142,
"count": 1,
"self": 0.10176167999998142
}
}
}
}
}
}
}