ppo-Huggy / run_logs /timers.json
liajun's picture
Huggy
33faf2f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3980333805084229,
"min": 1.3980333805084229,
"max": 1.42847740650177,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72009.90625,
"min": 68572.8828125,
"max": 78066.8828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.83525535420098,
"min": 78.42448330683625,
"max": 390.0232558139535,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49674.0,
"min": 48833.0,
"max": 50406.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49944.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49944.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4450883865356445,
"min": 0.10150477290153503,
"max": 2.4877641201019287,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1484.1685791015625,
"min": 12.992610931396484,
"max": 1486.9716796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7981177197256826,
"min": 1.9031688096001744,
"max": 3.9670242752195892,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2305.4574558734894,
"min": 243.60560762882233,
"max": 2315.445855140686,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7981177197256826,
"min": 1.9031688096001744,
"max": 3.9670242752195892,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2305.4574558734894,
"min": 243.60560762882233,
"max": 2315.445855140686,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01529102443989056,
"min": 0.012683323820238002,
"max": 0.021422218280349625,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04587307331967168,
"min": 0.025366647640476005,
"max": 0.056813741535491624,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05709801279008389,
"min": 0.021604261423150698,
"max": 0.0650353603065014,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17129403837025167,
"min": 0.043208522846301396,
"max": 0.19510608091950418,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1382489539500058e-06,
"min": 3.1382489539500058e-06,
"max": 0.0002952822015726,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.414746861850017e-06,
"min": 9.414746861850017e-06,
"max": 0.0008440653186449,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10104605000000001,
"min": 0.10104605000000001,
"max": 0.19842739999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30313815000000005,
"min": 0.2072238,
"max": 0.5813551000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.21978950000001e-05,
"min": 6.21978950000001e-05,
"max": 0.004921527259999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001865936850000003,
"min": 0.0001865936850000003,
"max": 0.014069619489999999,
"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": "1763730675",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/content/ml-agents/ml-agents/ml-agents/ml-agents/mlagents/trainers/learn.py config/ppo/Huggy.yaml --env=./ml-agents/trained-envs-executables/linux/Huggy/Huggy.x86_64 --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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1763733108"
},
"total": 2432.689730858,
"count": 1,
"self": 0.4795832390000214,
"children": {
"run_training.setup": {
"total": 0.023672573999874658,
"count": 1,
"self": 0.023672573999874658
},
"TrainerController.start_learning": {
"total": 2432.186475045,
"count": 1,
"self": 4.103454809930554,
"children": {
"TrainerController._reset_env": {
"total": 3.475104918999932,
"count": 1,
"self": 3.475104918999932
},
"TrainerController.advance": {
"total": 2424.5061960260696,
"count": 232413,
"self": 4.021660733299996,
"children": {
"env_step": {
"total": 1969.4518347499088,
"count": 232413,
"self": 1586.325293643758,
"children": {
"SubprocessEnvManager._take_step": {
"total": 380.57139163104307,
"count": 232413,
"self": 14.924012989044058,
"children": {
"TorchPolicy.evaluate": {
"total": 365.647378641999,
"count": 223016,
"self": 365.647378641999
}
}
},
"workers": {
"total": 2.5551494751077826,
"count": 232413,
"self": 0.0,
"children": {
"worker_root": {
"total": 2420.5761876848596,
"count": 232413,
"is_parallel": true,
"self": 1128.39808218586,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008226739998917765,
"count": 1,
"is_parallel": true,
"self": 0.0002539900001465867,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005686839997451898,
"count": 2,
"is_parallel": true,
"self": 0.0005686839997451898
}
}
},
"UnityEnvironment.step": {
"total": 0.028231935000121666,
"count": 1,
"is_parallel": true,
"self": 0.00027049699997405696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001893759999802569,
"count": 1,
"is_parallel": true,
"self": 0.0001893759999802569
},
"communicator.exchange": {
"total": 0.027106405000040468,
"count": 1,
"is_parallel": true,
"self": 0.027106405000040468
},
"steps_from_proto": {
"total": 0.0006656570001268847,
"count": 1,
"is_parallel": true,
"self": 0.0001885720002974267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047708499982945796,
"count": 2,
"is_parallel": true,
"self": 0.00047708499982945796
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1292.1781054989997,
"count": 232412,
"is_parallel": true,
"self": 36.080480499199666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.3241028968755,
"count": 232412,
"is_parallel": true,
"self": 79.3241028968755
},
"communicator.exchange": {
"total": 1091.590003716,
"count": 232412,
"is_parallel": true,
"self": 1091.590003716
},
"steps_from_proto": {
"total": 85.18351838692456,
"count": 232412,
"is_parallel": true,
"self": 29.90867866892745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.27483971799711,
"count": 464824,
"is_parallel": true,
"self": 55.27483971799711
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 451.03270054286077,
"count": 232413,
"self": 5.961612580872043,
"children": {
"process_trajectory": {
"total": 145.88148237798737,
"count": 232413,
"self": 144.80918942998824,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0722929479991308,
"count": 10,
"self": 1.0722929479991308
}
}
},
"_update_policy": {
"total": 299.18960558400136,
"count": 97,
"self": 237.73939609301033,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.45020949099103,
"count": 2910,
"self": 61.45020949099103
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.014999725157395e-06,
"count": 1,
"self": 1.014999725157395e-06
},
"TrainerController._save_models": {
"total": 0.10171827500016661,
"count": 1,
"self": 0.001843542000187881,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09987473299997873,
"count": 1,
"self": 0.09987473299997873
}
}
}
}
}
}
}