ppo-Pyramid / run_logs /timers.json
Isaac009's picture
Pyramid
12b11fe
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.15880054235458374,
"min": 0.1491870880126953,
"max": 1.4237074851989746,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4756.39404296875,
"min": 4506.6435546875,
"max": 43189.58984375,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999966.0,
"min": 29999.0,
"max": 2999966.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999966.0,
"min": 29999.0,
"max": 2999966.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7293675541877747,
"min": -0.10468761622905731,
"max": 0.8276109099388123,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 218.81027221679688,
"min": -25.22971534729004,
"max": 244.1452178955078,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.014533614739775658,
"min": -0.014890884980559349,
"max": 0.3038572371006012,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.360084533691406,
"min": -4.360084533691406,
"max": 72.92573547363281,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07048888819519473,
"min": 0.06428048918037564,
"max": 0.07384384130487245,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9868444347327263,
"min": 0.5009604268530036,
"max": 1.103320527123287,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01726482123129509,
"min": 0.00015504219309485907,
"max": 0.01830769369206835,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24170749723813129,
"min": 0.002170590703328027,
"max": 0.2563077116889569,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.493292359411904e-06,
"min": 1.493292359411904e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.0906093031766657e-05,
"min": 2.0906093031766657e-05,
"max": 0.003969315376894899,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049773095238097,
"min": 0.10049773095238097,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4069682333333335,
"min": 1.3962282666666668,
"max": 2.797511066666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.972332214285711e-05,
"min": 5.972332214285711e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008361265099999996,
"min": 0.0008361265099999996,
"max": 0.13231819949,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007824358530342579,
"min": 0.007093322928994894,
"max": 0.44081321358680725,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10954102128744125,
"min": 0.09930652379989624,
"max": 3.0856924057006836,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 224.0077519379845,
"min": 224.0077519379845,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28897.0,
"min": 16798.0,
"max": 32893.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7604837052581845,
"min": -0.9999375520274043,
"max": 1.7770454422994093,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 227.10239797830582,
"min": -31.998001664876938,
"max": 234.56999838352203,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7604837052581845,
"min": -0.9999375520274043,
"max": 1.7770454422994093,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 227.10239797830582,
"min": -31.998001664876938,
"max": 234.56999838352203,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.018140086486562002,
"min": 0.018140086486562002,
"max": 8.070416858967613,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.3400711567664985,
"min": 2.1746065304832882,
"max": 137.19708660244942,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1682474312",
"python_version": "3.9.16 (main, Apr 26 2023, 09:57:11) \n[GCC 9.4.0]",
"command_line_arguments": "/home/isaac/python_envs/py3916_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"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": "1682477516"
},
"total": 3204.198108993005,
"count": 1,
"self": 0.21982589199615177,
"children": {
"run_training.setup": {
"total": 0.03144663400598802,
"count": 1,
"self": 0.03144663400598802
},
"TrainerController.start_learning": {
"total": 3203.946836467003,
"count": 1,
"self": 3.4579225898633013,
"children": {
"TrainerController._reset_env": {
"total": 2.4951792289939476,
"count": 1,
"self": 2.4951792289939476
},
"TrainerController.advance": {
"total": 3197.928210208149,
"count": 194499,
"self": 3.4057235012442106,
"children": {
"env_step": {
"total": 1901.5275820100505,
"count": 194499,
"self": 1654.5325522463245,
"children": {
"SubprocessEnvManager._take_step": {
"total": 244.9089605788613,
"count": 194499,
"self": 9.158337061584461,
"children": {
"TorchPolicy.evaluate": {
"total": 235.75062351727684,
"count": 187559,
"self": 235.75062351727684
}
}
},
"workers": {
"total": 2.086069184864755,
"count": 194499,
"self": 0.0,
"children": {
"worker_root": {
"total": 3199.942962541085,
"count": 194499,
"is_parallel": true,
"self": 1760.6421606685471,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001044902004650794,
"count": 1,
"is_parallel": true,
"self": 0.00025916101003531367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007857409946154803,
"count": 8,
"is_parallel": true,
"self": 0.0007857409946154803
}
}
},
"UnityEnvironment.step": {
"total": 0.026606883999193087,
"count": 1,
"is_parallel": true,
"self": 0.00020751100964844227,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002081889979308471,
"count": 1,
"is_parallel": true,
"self": 0.0002081889979308471
},
"communicator.exchange": {
"total": 0.02545185999770183,
"count": 1,
"is_parallel": true,
"self": 0.02545185999770183
},
"steps_from_proto": {
"total": 0.0007393239939119667,
"count": 1,
"is_parallel": true,
"self": 0.00018399801047053188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005553259834414348,
"count": 8,
"is_parallel": true,
"self": 0.0005553259834414348
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1439.3008018725377,
"count": 194498,
"is_parallel": true,
"self": 40.4522011855006,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 32.99715649262362,
"count": 194498,
"is_parallel": true,
"self": 32.99715649262362
},
"communicator.exchange": {
"total": 1229.505049947431,
"count": 194498,
"is_parallel": true,
"self": 1229.505049947431
},
"steps_from_proto": {
"total": 136.34639424698253,
"count": 194498,
"is_parallel": true,
"self": 33.58424235753773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 102.7621518894448,
"count": 1555984,
"is_parallel": true,
"self": 102.7621518894448
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1292.994904696854,
"count": 194499,
"self": 5.539375349835609,
"children": {
"process_trajectory": {
"total": 228.17791947915975,
"count": 194499,
"self": 227.73186403216096,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4460554469987983,
"count": 6,
"self": 0.4460554469987983
}
}
},
"_update_policy": {
"total": 1059.2776098678587,
"count": 1397,
"self": 694.0839651809074,
"children": {
"TorchPPOOptimizer.update": {
"total": 365.1936446869513,
"count": 68382,
"self": 365.1936446869513
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.310009095817804e-07,
"count": 1,
"self": 7.310009095817804e-07
},
"TrainerController._save_models": {
"total": 0.06552370899589732,
"count": 1,
"self": 0.0009835619857767597,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06454014701012056,
"count": 1,
"self": 0.06454014701012056
}
}
}
}
}
}
}