ppo-Huggy / run_logs /timers.json
anderslindstrom's picture
Huggy
11f8c16 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4053674936294556,
"min": 1.4053674936294556,
"max": 1.424362301826477,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70741.984375,
"min": 68297.03125,
"max": 75523.515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.59322033898304,
"min": 81.8905472636816,
"max": 383.53435114503816,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49167.0,
"min": 49167.0,
"max": 50243.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49855.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49855.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.392244338989258,
"min": -0.07105459272861481,
"max": 2.4674038887023926,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1270.28173828125,
"min": -9.237096786499023,
"max": 1439.3623046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6051301289412936,
"min": 1.7442445704570184,
"max": 3.9101939320198595,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1914.3240984678268,
"min": 226.75179415941238,
"max": 2250.251417338848,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6051301289412936,
"min": 1.7442445704570184,
"max": 3.9101939320198595,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1914.3240984678268,
"min": 226.75179415941238,
"max": 2250.251417338848,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014066213207924094,
"min": 0.013974178547990353,
"max": 0.02110111481597414,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04219863962377228,
"min": 0.027948357095980706,
"max": 0.05914573338692814,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0530243479543262,
"min": 0.023631406389176844,
"max": 0.06633506659418345,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1590730438629786,
"min": 0.04726281277835369,
"max": 0.17745810945828755,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4282988572666695e-06,
"min": 3.4282988572666695e-06,
"max": 0.00029537242654252495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0284896571800009e-05,
"min": 1.0284896571800009e-05,
"max": 0.0008440588686470499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114273333333333,
"min": 0.10114273333333333,
"max": 0.198457475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034282,
"min": 0.20746154999999994,
"max": 0.5813529499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.702239333333339e-05,
"min": 6.702239333333339e-05,
"max": 0.0049230280025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020106718000000015,
"min": 0.00020106718000000015,
"max": 0.014069512204999999,
"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": "1747894189",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747896163"
},
"total": 1974.064832122,
"count": 1,
"self": 0.32091601100000844,
"children": {
"run_training.setup": {
"total": 0.020446259999971517,
"count": 1,
"self": 0.020446259999971517
},
"TrainerController.start_learning": {
"total": 1973.7234698510001,
"count": 1,
"self": 3.8704283060449143,
"children": {
"TrainerController._reset_env": {
"total": 2.2115841370000453,
"count": 1,
"self": 2.2115841370000453
},
"TrainerController.advance": {
"total": 1967.5226784409554,
"count": 232451,
"self": 3.8977011837810096,
"children": {
"env_step": {
"total": 1530.9397395111566,
"count": 232451,
"self": 1161.2083610979525,
"children": {
"SubprocessEnvManager._take_step": {
"total": 367.2823728340843,
"count": 232451,
"self": 13.720615305205683,
"children": {
"TorchPolicy.evaluate": {
"total": 353.5617575288786,
"count": 223038,
"self": 353.5617575288786
}
}
},
"workers": {
"total": 2.4490055791197847,
"count": 232451,
"self": 0.0,
"children": {
"worker_root": {
"total": 1966.815399801921,
"count": 232451,
"is_parallel": true,
"self": 1032.2556265338585,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008838290000312554,
"count": 1,
"is_parallel": true,
"self": 0.000244806000182507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006390229998487484,
"count": 2,
"is_parallel": true,
"self": 0.0006390229998487484
}
}
},
"UnityEnvironment.step": {
"total": 0.02243787599991265,
"count": 1,
"is_parallel": true,
"self": 0.00019378599972696975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015776000009282143,
"count": 1,
"is_parallel": true,
"self": 0.00015776000009282143
},
"communicator.exchange": {
"total": 0.020196287000089796,
"count": 1,
"is_parallel": true,
"self": 0.020196287000089796
},
"steps_from_proto": {
"total": 0.001890043000003061,
"count": 1,
"is_parallel": true,
"self": 0.0001256539997029904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017643890003000706,
"count": 2,
"is_parallel": true,
"self": 0.0017643890003000706
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 934.5597732680626,
"count": 232450,
"is_parallel": true,
"self": 25.333524230284866,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 47.926198573941974,
"count": 232450,
"is_parallel": true,
"self": 47.926198573941974
},
"communicator.exchange": {
"total": 803.9645875719234,
"count": 232450,
"is_parallel": true,
"self": 803.9645875719234
},
"steps_from_proto": {
"total": 57.33546289191236,
"count": 232450,
"is_parallel": true,
"self": 22.27362831805317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.06183457385919,
"count": 464900,
"is_parallel": true,
"self": 35.06183457385919
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 432.6852377460177,
"count": 232451,
"self": 5.881528956960665,
"children": {
"process_trajectory": {
"total": 143.98196592305567,
"count": 232451,
"self": 142.8804839070558,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1014820159998635,
"count": 10,
"self": 1.1014820159998635
}
}
},
"_update_policy": {
"total": 282.8217428660014,
"count": 97,
"self": 232.0134143660041,
"children": {
"TorchPPOOptimizer.update": {
"total": 50.80832849999729,
"count": 2910,
"self": 50.80832849999729
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0009998732130043e-06,
"count": 1,
"self": 1.0009998732130043e-06
},
"TrainerController._save_models": {
"total": 0.11877796599992507,
"count": 1,
"self": 0.001582700000199111,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11719526599972596,
"count": 1,
"self": 0.11719526599972596
}
}
}
}
}
}
}