ppo-Huggy / run_logs /timers.json
abdullahhatem's picture
Huggy
6d53045 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4020673036575317,
"min": 1.4020673036575317,
"max": 1.4262479543685913,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69665.921875,
"min": 68863.78125,
"max": 77884.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.38762214983713,
"min": 75.68817204301075,
"max": 419.3333333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49358.0,
"min": 49273.0,
"max": 50320.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999965.0,
"min": 49876.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999965.0,
"min": 49876.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4916834831237793,
"min": 0.0006726078572683036,
"max": 2.5215532779693604,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1529.8936767578125,
"min": 0.0800403356552124,
"max": 1602.8875732421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.924050082892471,
"min": 1.8773164075462758,
"max": 4.031262566095843,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2409.366750895977,
"min": 223.40065249800682,
"max": 2514.686445236206,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.924050082892471,
"min": 1.8773164075462758,
"max": 4.031262566095843,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2409.366750895977,
"min": 223.40065249800682,
"max": 2514.686445236206,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015131104090768429,
"min": 0.013903566038425196,
"max": 0.021601734033902177,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04539331227230529,
"min": 0.027807132076850392,
"max": 0.05707334255372795,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05926930287645923,
"min": 0.024048947956826952,
"max": 0.06304072013331784,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17780790862937768,
"min": 0.048904151096940046,
"max": 0.18912216039995353,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8207987264333325e-06,
"min": 3.8207987264333325e-06,
"max": 0.00029533537655487504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1462396179299997e-05,
"min": 1.1462396179299997e-05,
"max": 0.0008440185186604998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127356666666669,
"min": 0.10127356666666669,
"max": 0.19844512500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30382070000000005,
"min": 0.20768014999999995,
"max": 0.5813395000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.355097666666666e-05,
"min": 7.355097666666666e-05,
"max": 0.004922411737500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022065293,
"min": 0.00022065293,
"max": 0.014068841049999998,
"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": "1740312577",
"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": "1740315142"
},
"total": 2564.95207128,
"count": 1,
"self": 0.4415456080000695,
"children": {
"run_training.setup": {
"total": 0.023979241999995793,
"count": 1,
"self": 0.023979241999995793
},
"TrainerController.start_learning": {
"total": 2564.48654643,
"count": 1,
"self": 4.688149198143492,
"children": {
"TrainerController._reset_env": {
"total": 3.4820723939999425,
"count": 1,
"self": 3.4820723939999425
},
"TrainerController.advance": {
"total": 2556.1981034558567,
"count": 232941,
"self": 5.050826988895096,
"children": {
"env_step": {
"total": 2064.9441964370735,
"count": 232941,
"self": 1623.2254522011433,
"children": {
"SubprocessEnvManager._take_step": {
"total": 438.7791141070436,
"count": 232941,
"self": 17.008358997076584,
"children": {
"TorchPolicy.evaluate": {
"total": 421.770755109967,
"count": 222854,
"self": 421.770755109967
}
}
},
"workers": {
"total": 2.93963012888662,
"count": 232941,
"self": 0.0,
"children": {
"worker_root": {
"total": 2556.663034163028,
"count": 232941,
"is_parallel": true,
"self": 1237.7488786760296,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012516589999904681,
"count": 1,
"is_parallel": true,
"self": 0.0002705930000956869,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009810659998947813,
"count": 2,
"is_parallel": true,
"self": 0.0009810659998947813
}
}
},
"UnityEnvironment.step": {
"total": 0.058519487000012305,
"count": 1,
"is_parallel": true,
"self": 0.00034555600018393307,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017803600007937348,
"count": 1,
"is_parallel": true,
"self": 0.00017803600007937348
},
"communicator.exchange": {
"total": 0.05719902399982857,
"count": 1,
"is_parallel": true,
"self": 0.05719902399982857
},
"steps_from_proto": {
"total": 0.0007968709999204293,
"count": 1,
"is_parallel": true,
"self": 0.00026204899995718733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000534821999963242,
"count": 2,
"is_parallel": true,
"self": 0.000534821999963242
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1318.9141554869984,
"count": 232940,
"is_parallel": true,
"self": 38.31499972289771,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.66146859909281,
"count": 232940,
"is_parallel": true,
"self": 85.66146859909281
},
"communicator.exchange": {
"total": 1103.599212079915,
"count": 232940,
"is_parallel": true,
"self": 1103.599212079915
},
"steps_from_proto": {
"total": 91.3384750850928,
"count": 232940,
"is_parallel": true,
"self": 33.91745966716326,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.42101541792954,
"count": 465880,
"is_parallel": true,
"self": 57.42101541792954
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.20308002988804,
"count": 232941,
"self": 6.978153383819063,
"children": {
"process_trajectory": {
"total": 178.904558308069,
"count": 232941,
"self": 177.44073579106907,
"children": {
"RLTrainer._checkpoint": {
"total": 1.463822516999926,
"count": 10,
"self": 1.463822516999926
}
}
},
"_update_policy": {
"total": 300.320368338,
"count": 97,
"self": 236.24917013900813,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.07119819899185,
"count": 2910,
"self": 64.07119819899185
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.119999049289618e-07,
"count": 1,
"self": 9.119999049289618e-07
},
"TrainerController._save_models": {
"total": 0.11822046999986924,
"count": 1,
"self": 0.0017629499998292886,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11645752000003995,
"count": 1,
"self": 0.11645752000003995
}
}
}
}
}
}
}