ppo-Huggy / run_logs /timers.json
oferk's picture
Huggy
7272ab6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4021601676940918,
"min": 1.4021601676940918,
"max": 1.4265726804733276,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70101.0,
"min": 69253.3984375,
"max": 76026.421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.4054054054054,
"min": 75.44976816074188,
"max": 388.07751937984494,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49376.0,
"min": 48816.0,
"max": 50176.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49441.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49441.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3935160636901855,
"min": 0.02368725836277008,
"max": 2.511087656021118,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1416.9615478515625,
"min": 3.0319690704345703,
"max": 1541.807861328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6175249913657033,
"min": 1.7207311515230685,
"max": 4.050856757824118,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2141.5747948884964,
"min": 220.25358739495277,
"max": 2487.2260493040085,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6175249913657033,
"min": 1.7207311515230685,
"max": 4.050856757824118,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2141.5747948884964,
"min": 220.25358739495277,
"max": 2487.2260493040085,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016357140662148596,
"min": 0.013367071256895239,
"max": 0.018946547529453208,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04907142198644578,
"min": 0.026734142513790478,
"max": 0.05683964258835962,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059280750362409484,
"min": 0.023497374759366113,
"max": 0.06227955215921004,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17784225108722845,
"min": 0.046994749518732226,
"max": 0.18520423583686352,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7169987610333343e-06,
"min": 3.7169987610333343e-06,
"max": 0.00029526690157769995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1150996283100003e-05,
"min": 1.1150996283100003e-05,
"max": 0.0008438460187180001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012389666666667,
"min": 0.1012389666666667,
"max": 0.1984223,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30371690000000007,
"min": 0.20761269999999998,
"max": 0.5812820000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.182443666666669e-05,
"min": 7.182443666666669e-05,
"max": 0.00492127277,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021547331000000005,
"min": 0.00021547331000000005,
"max": 0.0140659718,
"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": "1746620762",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1746623232"
},
"total": 2470.078936931,
"count": 1,
"self": 0.4362574780002433,
"children": {
"run_training.setup": {
"total": 0.03217787800008409,
"count": 1,
"self": 0.03217787800008409
},
"TrainerController.start_learning": {
"total": 2469.610501575,
"count": 1,
"self": 4.496024625046175,
"children": {
"TrainerController._reset_env": {
"total": 3.449957162000146,
"count": 1,
"self": 3.449957162000146
},
"TrainerController.advance": {
"total": 2461.5516947359533,
"count": 232890,
"self": 4.619690244913272,
"children": {
"env_step": {
"total": 1975.6095513709392,
"count": 232890,
"self": 1559.0740299767572,
"children": {
"SubprocessEnvManager._take_step": {
"total": 413.9025406822004,
"count": 232890,
"self": 15.89777988321498,
"children": {
"TorchPolicy.evaluate": {
"total": 398.00476079898544,
"count": 222952,
"self": 398.00476079898544
}
}
},
"workers": {
"total": 2.632980711981645,
"count": 232890,
"self": 0.0,
"children": {
"worker_root": {
"total": 2462.3787814340762,
"count": 232890,
"is_parallel": true,
"self": 1190.5379953820961,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008847939998304355,
"count": 1,
"is_parallel": true,
"self": 0.0002412229998753901,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006435709999550454,
"count": 2,
"is_parallel": true,
"self": 0.0006435709999550454
}
}
},
"UnityEnvironment.step": {
"total": 0.032189628999958586,
"count": 1,
"is_parallel": true,
"self": 0.0002884499999709078,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020678600003520842,
"count": 1,
"is_parallel": true,
"self": 0.00020678600003520842
},
"communicator.exchange": {
"total": 0.029195665999850462,
"count": 1,
"is_parallel": true,
"self": 0.029195665999850462
},
"steps_from_proto": {
"total": 0.002498727000102008,
"count": 1,
"is_parallel": true,
"self": 0.00019949399984398042,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022992330002580275,
"count": 2,
"is_parallel": true,
"self": 0.0022992330002580275
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1271.84078605198,
"count": 232889,
"is_parallel": true,
"self": 36.67715813103723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.7588563340446,
"count": 232889,
"is_parallel": true,
"self": 82.7588563340446
},
"communicator.exchange": {
"total": 1064.1214254810357,
"count": 232889,
"is_parallel": true,
"self": 1064.1214254810357
},
"steps_from_proto": {
"total": 88.28334610586262,
"count": 232889,
"is_parallel": true,
"self": 32.75092908783108,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.53241701803154,
"count": 465778,
"is_parallel": true,
"self": 55.53241701803154
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.32245312010104,
"count": 232890,
"self": 6.562463436148391,
"children": {
"process_trajectory": {
"total": 168.9397766479492,
"count": 232890,
"self": 167.63343520294848,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3063414450007258,
"count": 10,
"self": 1.3063414450007258
}
}
},
"_update_policy": {
"total": 305.82021303600345,
"count": 97,
"self": 243.50081913400845,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.319393901995,
"count": 2910,
"self": 62.319393901995
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0320000001229346e-06,
"count": 1,
"self": 1.0320000001229346e-06
},
"TrainerController._save_models": {
"total": 0.11282402000006186,
"count": 1,
"self": 0.0017502760001661954,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11107374399989567,
"count": 1,
"self": 0.11107374399989567
}
}
}
}
}
}
}