ppo-Pyramids / run_logs /timers.json
jetfan-xin's picture
First push of trained PPO model on Pyramids
f08c1a3 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3166414499282837,
"min": 0.3166414499282837,
"max": 1.4837660789489746,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9549.90625,
"min": 9549.90625,
"max": 45011.52734375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989948.0,
"min": 29952.0,
"max": 989948.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989948.0,
"min": 29952.0,
"max": 989948.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5113525986671448,
"min": -0.09560375660657883,
"max": 0.5113525986671448,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 139.59925842285156,
"min": -23.1361083984375,
"max": 139.59925842285156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.011570850387215614,
"min": 0.0013953106245025992,
"max": 0.29088106751441956,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.158842086791992,
"min": 0.36696669459342957,
"max": 70.10234069824219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06807322610984556,
"min": 0.0651489318336565,
"max": 0.07737194881418048,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0210983916476835,
"min": 0.48964068805246924,
"max": 1.0300690002331976,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01653507004666608,
"min": 0.0008424101729033208,
"max": 0.017003003816907513,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24802605069999117,
"min": 0.01095133224774317,
"max": 0.24802605069999117,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.474937508386669e-06,
"min": 7.474937508386669e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011212406262580004,
"min": 0.00011212406262580004,
"max": 0.003632921889026099,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249161333333333,
"min": 0.10249161333333333,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5373742,
"min": 1.3886848,
"max": 2.6109739000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002589121720000001,
"min": 0.0002589121720000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038836825800000014,
"min": 0.0038836825800000014,
"max": 0.12111629261,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00881898682564497,
"min": 0.00881898682564497,
"max": 0.3842199742794037,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13228480517864227,
"min": 0.12609463930130005,
"max": 2.689539909362793,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 335.4096385542169,
"min": 335.4096385542169,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27839.0,
"min": 15984.0,
"max": 33189.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5440674588443286,
"min": -1.0000000521540642,
"max": 1.5440674588443286,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 128.15759908407927,
"min": -29.006201647222042,
"max": 128.15759908407927,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5440674588443286,
"min": -1.0000000521540642,
"max": 1.5440674588443286,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 128.15759908407927,
"min": -29.006201647222042,
"max": 128.15759908407927,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.030685754768313356,
"min": 0.030685754768313356,
"max": 8.42511613946408,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.5469176457700087,
"min": 2.5469176457700087,
"max": 134.80185823142529,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750783585",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/ltstorage/home/4xin/miniconda3/envs/rl_py310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids.x86_64 --run-id=PyramidsGPUTest --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750785163"
},
"total": 1577.424619921483,
"count": 1,
"self": 0.4248162331059575,
"children": {
"run_training.setup": {
"total": 0.0516781359910965,
"count": 1,
"self": 0.0516781359910965
},
"TrainerController.start_learning": {
"total": 1576.948125552386,
"count": 1,
"self": 0.8055871957913041,
"children": {
"TrainerController._reset_env": {
"total": 3.743472187779844,
"count": 1,
"self": 3.743472187779844
},
"TrainerController.advance": {
"total": 1572.303196429275,
"count": 63697,
"self": 0.8450221149250865,
"children": {
"env_step": {
"total": 1068.117137578316,
"count": 63697,
"self": 966.8781628590077,
"children": {
"SubprocessEnvManager._take_step": {
"total": 100.72575218696147,
"count": 63697,
"self": 2.7885951017960906,
"children": {
"TorchPolicy.evaluate": {
"total": 97.93715708516538,
"count": 62554,
"self": 97.93715708516538
}
}
},
"workers": {
"total": 0.5132225323468447,
"count": 63697,
"self": 0.0,
"children": {
"worker_root": {
"total": 1574.8682324932888,
"count": 63697,
"is_parallel": true,
"self": 683.8845944134519,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002007589675486088,
"count": 1,
"is_parallel": true,
"self": 0.0007919240742921829,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012156656011939049,
"count": 8,
"is_parallel": true,
"self": 0.0012156656011939049
}
}
},
"UnityEnvironment.step": {
"total": 0.02970798872411251,
"count": 1,
"is_parallel": true,
"self": 0.00025824736803770065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026993826031684875,
"count": 1,
"is_parallel": true,
"self": 0.00026993826031684875
},
"communicator.exchange": {
"total": 0.028303112834692,
"count": 1,
"is_parallel": true,
"self": 0.028303112834692
},
"steps_from_proto": {
"total": 0.0008766902610659599,
"count": 1,
"is_parallel": true,
"self": 0.0002178167924284935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006588734686374664,
"count": 8,
"is_parallel": true,
"self": 0.0006588734686374664
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 890.983638079837,
"count": 63696,
"is_parallel": true,
"self": 17.5128783704713,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.090136099606752,
"count": 63696,
"is_parallel": true,
"self": 12.090136099606752
},
"communicator.exchange": {
"total": 810.3930083326995,
"count": 63696,
"is_parallel": true,
"self": 810.3930083326995
},
"steps_from_proto": {
"total": 50.987615277059376,
"count": 63696,
"is_parallel": true,
"self": 10.624533851630986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.36308142542839,
"count": 509568,
"is_parallel": true,
"self": 40.36308142542839
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.34103673603386,
"count": 63697,
"self": 1.557245903648436,
"children": {
"process_trajectory": {
"total": 89.48766863066703,
"count": 63697,
"self": 89.24731530249119,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24035332817584276,
"count": 2,
"self": 0.24035332817584276
}
}
},
"_update_policy": {
"total": 412.2961222017184,
"count": 454,
"self": 220.17983413022012,
"children": {
"TorchPPOOptimizer.update": {
"total": 192.11628807149827,
"count": 22773,
"self": 192.11628807149827
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.292255759239197e-07,
"count": 1,
"self": 7.292255759239197e-07
},
"TrainerController._save_models": {
"total": 0.09586901031434536,
"count": 1,
"self": 0.004960021935403347,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09090898837894201,
"count": 1,
"self": 0.09090898837894201
}
}
}
}
}
}
}