ppo-huggy / run_logs /timers.json
ektvho's picture
Huggy
bd6f625 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4055136442184448,
"min": 1.4055136442184448,
"max": 1.4273067712783813,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69844.1875,
"min": 68824.890625,
"max": 77697.8671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.25164113785559,
"min": 103.15031315240084,
"max": 403.33870967741933,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49471.0,
"min": 49083.0,
"max": 50125.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999952.0,
"min": 49796.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999952.0,
"min": 49796.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2899961471557617,
"min": 0.036087892949581146,
"max": 2.3904964923858643,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1046.5281982421875,
"min": 4.4388108253479,
"max": 1123.30224609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.449550101089269,
"min": 1.9358396857250026,
"max": 3.9167212008874177,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1576.4443961977959,
"min": 238.10828134417534,
"max": 1807.354781448841,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.449550101089269,
"min": 1.9358396857250026,
"max": 3.9167212008874177,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1576.4443961977959,
"min": 238.10828134417534,
"max": 1807.354781448841,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017081133839080092,
"min": 0.012836287453440794,
"max": 0.021343025449702208,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.034162267678160184,
"min": 0.025672574906881587,
"max": 0.05683665493852459,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04815658622731765,
"min": 0.023582778250177704,
"max": 0.06086537775894006,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0963131724546353,
"min": 0.04716555650035541,
"max": 0.17774045368035635,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.537973487375001e-06,
"min": 4.537973487375001e-06,
"max": 0.0002953908765363749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.075946974750001e-06,
"min": 9.075946974750001e-06,
"max": 0.0008445702184766001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10151262500000001,
"min": 0.10151262500000001,
"max": 0.19846362500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20302525000000002,
"min": 0.20302525000000002,
"max": 0.5815234000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.547998750000007e-05,
"min": 8.547998750000007e-05,
"max": 0.0049233348875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017095997500000013,
"min": 0.00017095997500000013,
"max": 0.01407801766,
"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": "1734096318",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734098855"
},
"total": 2537.764130735,
"count": 1,
"self": 0.8133640800001558,
"children": {
"run_training.setup": {
"total": 0.060624325999981465,
"count": 1,
"self": 0.060624325999981465
},
"TrainerController.start_learning": {
"total": 2536.890142329,
"count": 1,
"self": 5.074341399992136,
"children": {
"TrainerController._reset_env": {
"total": 6.024347814999999,
"count": 1,
"self": 6.024347814999999
},
"TrainerController.advance": {
"total": 2525.6186033850076,
"count": 230912,
"self": 4.8829332301097566,
"children": {
"env_step": {
"total": 2009.0136882769661,
"count": 230912,
"self": 1578.0538071919739,
"children": {
"SubprocessEnvManager._take_step": {
"total": 427.93399369902875,
"count": 230912,
"self": 16.226274154894952,
"children": {
"TorchPolicy.evaluate": {
"total": 411.7077195441338,
"count": 222976,
"self": 411.7077195441338
}
}
},
"workers": {
"total": 3.0258873859635855,
"count": 230912,
"self": 0.0,
"children": {
"worker_root": {
"total": 2529.1974314979334,
"count": 230912,
"is_parallel": true,
"self": 1248.1995497019295,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009794320000082735,
"count": 1,
"is_parallel": true,
"self": 0.00028455300002860895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006948789999796645,
"count": 2,
"is_parallel": true,
"self": 0.0006948789999796645
}
}
},
"UnityEnvironment.step": {
"total": 0.030462554000052933,
"count": 1,
"is_parallel": true,
"self": 0.0004262260000587048,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019854900000382258,
"count": 1,
"is_parallel": true,
"self": 0.00019854900000382258
},
"communicator.exchange": {
"total": 0.029042946000004122,
"count": 1,
"is_parallel": true,
"self": 0.029042946000004122
},
"steps_from_proto": {
"total": 0.0007948329999862835,
"count": 1,
"is_parallel": true,
"self": 0.00021381900006645083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005810139999198327,
"count": 2,
"is_parallel": true,
"self": 0.0005810139999198327
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1280.9978817960039,
"count": 230911,
"is_parallel": true,
"self": 39.19603540291814,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.26403336207892,
"count": 230911,
"is_parallel": true,
"self": 82.26403336207892
},
"communicator.exchange": {
"total": 1067.7648152970687,
"count": 230911,
"is_parallel": true,
"self": 1067.7648152970687
},
"steps_from_proto": {
"total": 91.77299773393827,
"count": 230911,
"is_parallel": true,
"self": 31.895271306051995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.87772642788627,
"count": 461822,
"is_parallel": true,
"self": 59.87772642788627
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 511.72198187793157,
"count": 230912,
"self": 7.730257264868612,
"children": {
"process_trajectory": {
"total": 159.65651349906244,
"count": 230912,
"self": 158.2715203720631,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3849931269993476,
"count": 10,
"self": 1.3849931269993476
}
}
},
"_update_policy": {
"total": 344.3352111140005,
"count": 96,
"self": 276.0355679329923,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.29964318100821,
"count": 2880,
"self": 68.29964318100821
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3480002962751314e-06,
"count": 1,
"self": 1.3480002962751314e-06
},
"TrainerController._save_models": {
"total": 0.17284838099976696,
"count": 1,
"self": 0.0030158319996189675,
"children": {
"RLTrainer._checkpoint": {
"total": 0.169832549000148,
"count": 1,
"self": 0.169832549000148
}
}
}
}
}
}
}