ppo-Huggy / run_logs /timers.json
thackerhelik's picture
Uploading Huggy PPO trained model
17435fa
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015685319900513,
"min": 1.4015685319900513,
"max": 1.4250222444534302,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70127.484375,
"min": 68543.21875,
"max": 77701.9921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.13486842105263,
"min": 74.3328313253012,
"max": 394.251968503937,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49330.0,
"min": 48732.0,
"max": 50070.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999939.0,
"min": 49494.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999939.0,
"min": 49494.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4471335411071777,
"min": 0.10226879268884659,
"max": 2.496046781539917,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1487.857177734375,
"min": 12.885868072509766,
"max": 1614.8572998046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.749992159538363,
"min": 1.7913193459075594,
"max": 4.086373215235994,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2279.995232999325,
"min": 225.7062375843525,
"max": 2536.526078104973,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.749992159538363,
"min": 1.7913193459075594,
"max": 4.086373215235994,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2279.995232999325,
"min": 225.7062375843525,
"max": 2536.526078104973,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018485855385531772,
"min": 0.012831107304858355,
"max": 0.02076646498462651,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05545756615659532,
"min": 0.02566221460971671,
"max": 0.05727545098755703,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05515417891244093,
"min": 0.020971935770163933,
"max": 0.05858019764224688,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1654625367373228,
"min": 0.041943871540327866,
"max": 0.17354041437307993,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.644648785149991e-06,
"min": 3.644648785149991e-06,
"max": 0.0002952820515726499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0933946355449973e-05,
"min": 1.0933946355449973e-05,
"max": 0.0008438085187304998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121485000000001,
"min": 0.10121485000000001,
"max": 0.19842735000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364455,
"min": 0.20756940000000004,
"max": 0.5812695000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.062101499999986e-05,
"min": 7.062101499999986e-05,
"max": 0.004921524765000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021186304499999956,
"min": 0.00021186304499999956,
"max": 0.014065348050000002,
"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": "1681325207",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "1681327778"
},
"total": 2570.5223004379995,
"count": 1,
"self": 0.43541084399930696,
"children": {
"run_training.setup": {
"total": 0.11323816800017994,
"count": 1,
"self": 0.11323816800017994
},
"TrainerController.start_learning": {
"total": 2569.9736514260003,
"count": 1,
"self": 5.059288326953265,
"children": {
"TrainerController._reset_env": {
"total": 4.078908188000014,
"count": 1,
"self": 4.078908188000014
},
"TrainerController.advance": {
"total": 2560.7126357450475,
"count": 233015,
"self": 5.204200102166396,
"children": {
"env_step": {
"total": 2009.670053181908,
"count": 233015,
"self": 1707.459661736853,
"children": {
"SubprocessEnvManager._take_step": {
"total": 298.9801697990431,
"count": 233015,
"self": 17.856201783031338,
"children": {
"TorchPolicy.evaluate": {
"total": 281.12396801601176,
"count": 222955,
"self": 281.12396801601176
}
}
},
"workers": {
"total": 3.230221646012069,
"count": 233015,
"self": 0.0,
"children": {
"worker_root": {
"total": 2560.947524291002,
"count": 233015,
"is_parallel": true,
"self": 1158.521257161912,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008885649999683665,
"count": 1,
"is_parallel": true,
"self": 0.0002355769997848256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006529880001835409,
"count": 2,
"is_parallel": true,
"self": 0.0006529880001835409
}
}
},
"UnityEnvironment.step": {
"total": 0.029595276999998532,
"count": 1,
"is_parallel": true,
"self": 0.00033305500028291135,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023636199989596207,
"count": 1,
"is_parallel": true,
"self": 0.00023636199989596207
},
"communicator.exchange": {
"total": 0.028295455000034053,
"count": 1,
"is_parallel": true,
"self": 0.028295455000034053
},
"steps_from_proto": {
"total": 0.0007304049997856055,
"count": 1,
"is_parallel": true,
"self": 0.0002181919999202364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005122129998653691,
"count": 2,
"is_parallel": true,
"self": 0.0005122129998653691
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1402.42626712909,
"count": 233014,
"is_parallel": true,
"self": 41.96712218618768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.11041278094149,
"count": 233014,
"is_parallel": true,
"self": 84.11041278094149
},
"communicator.exchange": {
"total": 1179.6252925219974,
"count": 233014,
"is_parallel": true,
"self": 1179.6252925219974
},
"steps_from_proto": {
"total": 96.72343963996354,
"count": 233014,
"is_parallel": true,
"self": 35.686762473025965,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.03667716693758,
"count": 466028,
"is_parallel": true,
"self": 61.03667716693758
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 545.838382460973,
"count": 233015,
"self": 8.227911842015146,
"children": {
"process_trajectory": {
"total": 142.14731309996296,
"count": 233015,
"self": 140.87302019396293,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2742929060000279,
"count": 10,
"self": 1.2742929060000279
}
}
},
"_update_policy": {
"total": 395.4631575189949,
"count": 97,
"self": 334.0299765389907,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.43318098000418,
"count": 2910,
"self": 61.43318098000418
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.729998626222368e-07,
"count": 1,
"self": 8.729998626222368e-07
},
"TrainerController._save_models": {
"total": 0.12281829299990932,
"count": 1,
"self": 0.0024555879999752506,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12036270499993407,
"count": 1,
"self": 0.12036270499993407
}
}
}
}
}
}
}