ppo-Huggy / run_logs /timers.json
Vermeer's picture
Huggy
d7adfbc
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4014852046966553,
"min": 1.4014852046966553,
"max": 1.4279470443725586,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70922.15625,
"min": 68198.46875,
"max": 78084.2265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.33443163097199,
"min": 80.41734860883797,
"max": 386.6461538461538,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49370.0,
"min": 49135.0,
"max": 50264.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999993.0,
"min": 49963.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999993.0,
"min": 49963.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4312219619750977,
"min": 0.1427093744277954,
"max": 2.461414098739624,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1475.751708984375,
"min": 18.409509658813477,
"max": 1475.751708984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7437582589452703,
"min": 1.8249101121296254,
"max": 3.8790942851234886,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2272.461263179779,
"min": 235.41340446472168,
"max": 2285.867290556431,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7437582589452703,
"min": 1.8249101121296254,
"max": 3.8790942851234886,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2272.461263179779,
"min": 235.41340446472168,
"max": 2285.867290556431,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016368478276369086,
"min": 0.014016652284772136,
"max": 0.020982783735962584,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04910543482910726,
"min": 0.02803330456954427,
"max": 0.060016162754133504,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059587915697031556,
"min": 0.02195444172248244,
"max": 0.06633281440784533,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17876374709109466,
"min": 0.04390888344496488,
"max": 0.17926055938005447,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.444198851966672e-06,
"min": 3.444198851966672e-06,
"max": 0.00029535945154685007,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0332596555900016e-05,
"min": 1.0332596555900016e-05,
"max": 0.0008442409685863502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114803333333332,
"min": 0.10114803333333332,
"max": 0.19845314999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30344409999999994,
"min": 0.20742179999999993,
"max": 0.58141365,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.728686333333344e-05,
"min": 6.728686333333344e-05,
"max": 0.004922812185,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020186059000000035,
"min": 0.00020186059000000035,
"max": 0.014072541135,
"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": "1694665782",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694668279"
},
"total": 2496.6372907269997,
"count": 1,
"self": 0.4447021779997158,
"children": {
"run_training.setup": {
"total": 0.06776805100003003,
"count": 1,
"self": 0.06776805100003003
},
"TrainerController.start_learning": {
"total": 2496.124820498,
"count": 1,
"self": 4.7454874089353325,
"children": {
"TrainerController._reset_env": {
"total": 4.152809585,
"count": 1,
"self": 4.152809585
},
"TrainerController.advance": {
"total": 2487.108109344065,
"count": 231849,
"self": 4.679702805104625,
"children": {
"env_step": {
"total": 1934.4781622619887,
"count": 231849,
"self": 1631.116433875849,
"children": {
"SubprocessEnvManager._take_step": {
"total": 300.331873563154,
"count": 231849,
"self": 17.115938928114815,
"children": {
"TorchPolicy.evaluate": {
"total": 283.21593463503916,
"count": 222952,
"self": 283.21593463503916
}
}
},
"workers": {
"total": 3.029854822985726,
"count": 231849,
"self": 0.0,
"children": {
"worker_root": {
"total": 2488.3428538420567,
"count": 231849,
"is_parallel": true,
"self": 1158.7483286159463,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009171269999797005,
"count": 1,
"is_parallel": true,
"self": 0.00025145200004317303,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006656749999365275,
"count": 2,
"is_parallel": true,
"self": 0.0006656749999365275
}
}
},
"UnityEnvironment.step": {
"total": 0.029885123999974894,
"count": 1,
"is_parallel": true,
"self": 0.0002871389999654639,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002042490000349062,
"count": 1,
"is_parallel": true,
"self": 0.0002042490000349062
},
"communicator.exchange": {
"total": 0.02863896899998508,
"count": 1,
"is_parallel": true,
"self": 0.02863896899998508
},
"steps_from_proto": {
"total": 0.0007547669999894424,
"count": 1,
"is_parallel": true,
"self": 0.00022691499998472864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005278520000047138,
"count": 2,
"is_parallel": true,
"self": 0.0005278520000047138
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.5945252261104,
"count": 231848,
"is_parallel": true,
"self": 39.60094785111278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.06535872904453,
"count": 231848,
"is_parallel": true,
"self": 86.06535872904453
},
"communicator.exchange": {
"total": 1102.7918128149918,
"count": 231848,
"is_parallel": true,
"self": 1102.7918128149918
},
"steps_from_proto": {
"total": 101.1364058309614,
"count": 231848,
"is_parallel": true,
"self": 38.360062669069066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.77634316189233,
"count": 463696,
"is_parallel": true,
"self": 62.77634316189233
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 547.9502442769713,
"count": 231849,
"self": 6.791414023963966,
"children": {
"process_trajectory": {
"total": 143.21121049800513,
"count": 231849,
"self": 141.78344961300468,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4277608850004526,
"count": 10,
"self": 1.4277608850004526
}
}
},
"_update_policy": {
"total": 397.94761975500217,
"count": 97,
"self": 338.19961643300167,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.7480033220005,
"count": 2910,
"self": 59.7480033220005
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0720000318542589e-06,
"count": 1,
"self": 1.0720000318542589e-06
},
"TrainerController._save_models": {
"total": 0.11841308800012484,
"count": 1,
"self": 0.0019314099999974133,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11648167800012743,
"count": 1,
"self": 0.11648167800012743
}
}
}
}
}
}
}