ppo-Huggy / run_logs /timers.json
ShuchengLi's picture
Huggy
07db918 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.413591742515564,
"min": 1.413591742515564,
"max": 1.4261857271194458,
"count": 21
},
"Huggy.Policy.Entropy.sum": {
"value": 70433.625,
"min": 68790.84375,
"max": 78462.0625,
"count": 21
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.39460370994941,
"min": 79.4669887278583,
"max": 412.0,
"count": 21
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49453.0,
"min": 49349.0,
"max": 50264.0,
"count": 21
},
"Huggy.Step.mean": {
"value": 1049981.0,
"min": 49939.0,
"max": 1049981.0,
"count": 21
},
"Huggy.Step.sum": {
"value": 1049981.0,
"min": 49939.0,
"max": 1049981.0,
"count": 21
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.448803186416626,
"min": 0.016848938539624214,
"max": 2.448803186416626,
"count": 21
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1452.1402587890625,
"min": 2.0387215614318848,
"max": 1460.108154296875,
"count": 21
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.081948327977983,
"min": 1.746083317216763,
"max": 4.081948327977983,
"count": 21
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2420.595358490944,
"min": 211.2760813832283,
"max": 2420.595358490944,
"count": 21
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.081948327977983,
"min": 1.746083317216763,
"max": 4.081948327977983,
"count": 21
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2420.595358490944,
"min": 211.2760813832283,
"max": 2420.595358490944,
"count": 21
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016580528721614324,
"min": 0.01404358515283093,
"max": 0.02089769240780394,
"count": 21
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04974158616484298,
"min": 0.02808717030566186,
"max": 0.05536879937571939,
"count": 21
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05209377656380335,
"min": 0.022341212847580512,
"max": 0.05565042154242595,
"count": 21
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15628132969141006,
"min": 0.044682425695161024,
"max": 0.16599063500761985,
"count": 21
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.00014568260143915003,
"min": 0.00014568260143915003,
"max": 0.00029535532654822495,
"count": 21
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.0004370478043174501,
"min": 0.00030674454775185,
"max": 0.0008442603185798998,
"count": 21
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.14856085,
"min": 0.14856085,
"max": 0.19845177500000002,
"count": 21
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.44568254999999996,
"min": 0.30224814999999994,
"max": 0.5814201,
"count": 21
},
"Huggy.Policy.Beta.mean": {
"value": 0.0024331864150000013,
"min": 0.0024331864150000013,
"max": 0.004922743572500001,
"count": 21
},
"Huggy.Policy.Beta.sum": {
"value": 0.0072995592450000035,
"min": 0.005122182684999999,
"max": 0.01407286299,
"count": 21
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 21
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 21
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1757388384",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757389660"
},
"total": 1275.4914446540001,
"count": 1,
"self": 0.26261759600038204,
"children": {
"run_training.setup": {
"total": 0.024376721999942674,
"count": 1,
"self": 0.024376721999942674
},
"TrainerController.start_learning": {
"total": 1275.2044503359998,
"count": 1,
"self": 2.1761519910478455,
"children": {
"TrainerController._reset_env": {
"total": 2.8808251200002815,
"count": 1,
"self": 2.8808251200002815
},
"TrainerController.advance": {
"total": 1269.9655601899517,
"count": 127275,
"self": 2.2121324310874115,
"children": {
"env_step": {
"total": 1024.505292088891,
"count": 127275,
"self": 808.7629019657397,
"children": {
"SubprocessEnvManager._take_step": {
"total": 214.37386926411455,
"count": 127275,
"self": 7.995520357123951,
"children": {
"TorchPolicy.evaluate": {
"total": 206.3783489069906,
"count": 122538,
"self": 206.3783489069906
}
}
},
"workers": {
"total": 1.3685208590368347,
"count": 127275,
"self": 0.0,
"children": {
"worker_root": {
"total": 1271.23122753794,
"count": 127275,
"is_parallel": true,
"self": 612.3824241829002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008616179998170992,
"count": 1,
"is_parallel": true,
"self": 0.000237816999288043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006238010005290562,
"count": 2,
"is_parallel": true,
"self": 0.0006238010005290562
}
}
},
"UnityEnvironment.step": {
"total": 0.03145316299969636,
"count": 1,
"is_parallel": true,
"self": 0.0003378420001354243,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019228600012866082,
"count": 1,
"is_parallel": true,
"self": 0.00019228600012866082
},
"communicator.exchange": {
"total": 0.030217278999771224,
"count": 1,
"is_parallel": true,
"self": 0.030217278999771224
},
"steps_from_proto": {
"total": 0.0007057559996610507,
"count": 1,
"is_parallel": true,
"self": 0.0002128489995811833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004929070000798674,
"count": 2,
"is_parallel": true,
"self": 0.0004929070000798674
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 658.8488033550398,
"count": 127274,
"is_parallel": true,
"self": 20.118133354973907,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 43.07272233700314,
"count": 127274,
"is_parallel": true,
"self": 43.07272233700314
},
"communicator.exchange": {
"total": 548.0269635960194,
"count": 127274,
"is_parallel": true,
"self": 548.0269635960194
},
"steps_from_proto": {
"total": 47.6309840670433,
"count": 127274,
"is_parallel": true,
"self": 17.58963046702229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.04135360002101,
"count": 254548,
"is_parallel": true,
"self": 30.04135360002101
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 243.24813566997318,
"count": 127275,
"self": 3.2857249380404028,
"children": {
"process_trajectory": {
"total": 76.49973555693259,
"count": 127275,
"self": 75.87892890793228,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6208066490003148,
"count": 5,
"self": 0.6208066490003148
}
}
},
"_update_policy": {
"total": 163.4626751750002,
"count": 53,
"self": 129.72795127200607,
"children": {
"TorchPPOOptimizer.update": {
"total": 33.73472390299412,
"count": 1590,
"self": 33.73472390299412
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.419000000169035e-06,
"count": 1,
"self": 1.419000000169035e-06
},
"TrainerController._save_models": {
"total": 0.1819116159999794,
"count": 1,
"self": 0.0025932700000339537,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17931834599994545,
"count": 1,
"self": 0.17931834599994545
}
}
}
}
}
}
}