ppo-Huggy / run_logs /timers.json
satvshr's picture
Huggy
edce045 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4113023281097412,
"min": 1.4113023281097412,
"max": 1.4349992275238037,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71440.125,
"min": 69738.015625,
"max": 78164.9921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.33333333333333,
"min": 73.37053571428571,
"max": 388.6434108527132,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49405.0,
"min": 48749.0,
"max": 50320.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49750.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49750.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.535510540008545,
"min": 0.2543376386165619,
"max": 2.5703957080841064,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1559.3389892578125,
"min": 32.55521774291992,
"max": 1663.843994140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.928878884102271,
"min": 1.8847154269460589,
"max": 4.027417289366085,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2416.2605137228966,
"min": 241.24357464909554,
"max": 2647.554938673973,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.928878884102271,
"min": 1.8847154269460589,
"max": 4.027417289366085,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2416.2605137228966,
"min": 241.24357464909554,
"max": 2647.554938673973,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015001373743224475,
"min": 0.014254080169161576,
"max": 0.01934605807788709,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04500412122967343,
"min": 0.02904224582622798,
"max": 0.05397009769027742,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.058410508020056616,
"min": 0.01975514820466439,
"max": 0.058712170893947285,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17523152406016984,
"min": 0.03951029640932878,
"max": 0.17613651268184186,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6418987860666724e-06,
"min": 3.6418987860666724e-06,
"max": 0.00029538802653732496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0925696358200017e-05,
"min": 1.0925696358200017e-05,
"max": 0.00084394576868475,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121393333333335,
"min": 0.10121393333333335,
"max": 0.19846267499999992,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036418000000001,
"min": 0.20755695,
"max": 0.5813152500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.057527333333346e-05,
"min": 7.057527333333346e-05,
"max": 0.004923287482500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021172582000000037,
"min": 0.00021172582000000037,
"max": 0.014067630974999999,
"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": "1723499171",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723501606"
},
"total": 2435.023780191,
"count": 1,
"self": 0.7504690869996011,
"children": {
"run_training.setup": {
"total": 0.061603466999997636,
"count": 1,
"self": 0.061603466999997636
},
"TrainerController.start_learning": {
"total": 2434.211707637,
"count": 1,
"self": 4.456667694855696,
"children": {
"TrainerController._reset_env": {
"total": 3.4626894430000448,
"count": 1,
"self": 3.4626894430000448
},
"TrainerController.advance": {
"total": 2426.1178312991447,
"count": 233506,
"self": 4.745730522214217,
"children": {
"env_step": {
"total": 1911.316006554928,
"count": 233506,
"self": 1579.2561362958536,
"children": {
"SubprocessEnvManager._take_step": {
"total": 329.21389134000634,
"count": 233506,
"self": 16.453992211115462,
"children": {
"TorchPolicy.evaluate": {
"total": 312.7598991288909,
"count": 223052,
"self": 312.7598991288909
}
}
},
"workers": {
"total": 2.845978919068102,
"count": 233506,
"self": 0.0,
"children": {
"worker_root": {
"total": 2426.756748399095,
"count": 233506,
"is_parallel": true,
"self": 1148.0941158781125,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009293859999957022,
"count": 1,
"is_parallel": true,
"self": 0.00024132900000495283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006880569999907493,
"count": 2,
"is_parallel": true,
"self": 0.0006880569999907493
}
}
},
"UnityEnvironment.step": {
"total": 0.05314327499996807,
"count": 1,
"is_parallel": true,
"self": 0.00045810099999243903,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002521899999692323,
"count": 1,
"is_parallel": true,
"self": 0.0002521899999692323
},
"communicator.exchange": {
"total": 0.0516306229999941,
"count": 1,
"is_parallel": true,
"self": 0.0516306229999941
},
"steps_from_proto": {
"total": 0.0008023610000122972,
"count": 1,
"is_parallel": true,
"self": 0.00023056699996004681,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005717940000522503,
"count": 2,
"is_parallel": true,
"self": 0.0005717940000522503
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1278.6626325209827,
"count": 233505,
"is_parallel": true,
"self": 38.91112364606238,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.62264684103735,
"count": 233505,
"is_parallel": true,
"self": 83.62264684103735
},
"communicator.exchange": {
"total": 1064.7820224608795,
"count": 233505,
"is_parallel": true,
"self": 1064.7820224608795
},
"steps_from_proto": {
"total": 91.34683957300348,
"count": 233505,
"is_parallel": true,
"self": 32.50649396987251,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.84034560313097,
"count": 467010,
"is_parallel": true,
"self": 58.84034560313097
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.0560942220025,
"count": 233506,
"self": 6.355903928832902,
"children": {
"process_trajectory": {
"total": 161.18619777617073,
"count": 233506,
"self": 159.69913686217046,
"children": {
"RLTrainer._checkpoint": {
"total": 1.487060914000267,
"count": 10,
"self": 1.487060914000267
}
}
},
"_update_policy": {
"total": 342.5139925169989,
"count": 97,
"self": 277.34216024800196,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.17183226899692,
"count": 2910,
"self": 65.17183226899692
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2809996405849233e-06,
"count": 1,
"self": 1.2809996405849233e-06
},
"TrainerController._save_models": {
"total": 0.17451791900020908,
"count": 1,
"self": 0.0027347950003786536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17178312399983042,
"count": 1,
"self": 0.17178312399983042
}
}
}
}
}
}
}