PyramidsPPO / run_logs /timers.json
kjmann's picture
upload from hf RL course
43d2375
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6544572114944458,
"min": 0.5971586108207703,
"max": 1.3204686641693115,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 19539.474609375,
"min": 17924.3125,
"max": 40057.73828125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989901.0,
"min": 29905.0,
"max": 989901.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989901.0,
"min": 29905.0,
"max": 989901.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.23381727933883667,
"min": -0.10308179259300232,
"max": 0.23381727933883667,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 60.55867385864258,
"min": -24.84271240234375,
"max": 60.55867385864258,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01532779447734356,
"min": 0.009356344118714333,
"max": 0.6371363401412964,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.9698987007141113,
"min": 2.2548789978027344,
"max": 151.00131225585938,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07052791839940291,
"min": 0.06572190059751828,
"max": 0.07555467268336015,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9873908575916408,
"min": 0.5288827087835211,
"max": 1.0778166331983097,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012037281072439494,
"min": 0.00014839098045144077,
"max": 0.013313138820001931,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1685219350141529,
"min": 0.00192908274586873,
"max": 0.17698423672449923,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.7808974064e-06,
"min": 7.7808974064e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001089325636896,
"min": 0.0001089325636896,
"max": 0.0033818189727271002,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025936,
"min": 0.1025936,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4363104,
"min": 1.3886848,
"max": 2.5272729,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026910063999999997,
"min": 0.00026910063999999997,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037674089599999995,
"min": 0.0037674089599999995,
"max": 0.11275456271000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010950866155326366,
"min": 0.010675571858882904,
"max": 0.605381429195404,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15331213176250458,
"min": 0.14945800602436066,
"max": 4.237669944763184,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 608.622641509434,
"min": 608.622641509434,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32257.0,
"min": 16832.0,
"max": 33516.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9097740440456955,
"min": -0.9999290844125133,
"max": 0.9097740440456955,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 49.12779837846756,
"min": -31.997201666235924,
"max": 49.12779837846756,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9097740440456955,
"min": -0.9999290844125133,
"max": 0.9097740440456955,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 49.12779837846756,
"min": -31.997201666235924,
"max": 49.12779837846756,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06893867443216516,
"min": 0.06893867443216516,
"max": 12.381299756029073,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.7226884193369187,
"min": 3.1808168863062747,
"max": 210.48209585249424,
"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": "1674808937",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674810820"
},
"total": 1882.5465722349995,
"count": 1,
"self": 0.44494050100001914,
"children": {
"run_training.setup": {
"total": 0.09785167699965314,
"count": 1,
"self": 0.09785167699965314
},
"TrainerController.start_learning": {
"total": 1882.0037800569999,
"count": 1,
"self": 1.098713159001818,
"children": {
"TrainerController._reset_env": {
"total": 5.890943396000239,
"count": 1,
"self": 5.890943396000239
},
"TrainerController.advance": {
"total": 1874.9313149869972,
"count": 63247,
"self": 1.1610906399732812,
"children": {
"env_step": {
"total": 1249.5489751540126,
"count": 63247,
"self": 1152.8465367319563,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.02336331405559,
"count": 63247,
"self": 3.9720894380857317,
"children": {
"TorchPolicy.evaluate": {
"total": 92.05127387596985,
"count": 62572,
"self": 31.10022710598105,
"children": {
"TorchPolicy.sample_actions": {
"total": 60.95104676998881,
"count": 62572,
"self": 60.95104676998881
}
}
}
}
},
"workers": {
"total": 0.6790751080006885,
"count": 63247,
"self": 0.0,
"children": {
"worker_root": {
"total": 1879.4027185421164,
"count": 63247,
"is_parallel": true,
"self": 814.4259908040667,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017525010002827912,
"count": 1,
"is_parallel": true,
"self": 0.0006469799996011716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011055210006816196,
"count": 8,
"is_parallel": true,
"self": 0.0011055210006816196
}
}
},
"UnityEnvironment.step": {
"total": 0.041232881999803794,
"count": 1,
"is_parallel": true,
"self": 0.0004557499992188241,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042342799997641123,
"count": 1,
"is_parallel": true,
"self": 0.00042342799997641123
},
"communicator.exchange": {
"total": 0.03886007800019797,
"count": 1,
"is_parallel": true,
"self": 0.03886007800019797
},
"steps_from_proto": {
"total": 0.0014936260004105861,
"count": 1,
"is_parallel": true,
"self": 0.00038568099989788607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011079450005127,
"count": 8,
"is_parallel": true,
"self": 0.0011079450005127
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1064.9767277380497,
"count": 63246,
"is_parallel": true,
"self": 25.90220179908647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 20.849585505045525,
"count": 63246,
"is_parallel": true,
"self": 20.849585505045525
},
"communicator.exchange": {
"total": 933.3841610669201,
"count": 63246,
"is_parallel": true,
"self": 933.3841610669201
},
"steps_from_proto": {
"total": 84.8407793669976,
"count": 63246,
"is_parallel": true,
"self": 19.50563916227793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.33514020471966,
"count": 505968,
"is_parallel": true,
"self": 65.33514020471966
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 624.2212491930113,
"count": 63247,
"self": 2.0043483190784173,
"children": {
"process_trajectory": {
"total": 136.63881536392864,
"count": 63247,
"self": 136.4577922489293,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1810231149993342,
"count": 2,
"self": 0.1810231149993342
}
}
},
"_update_policy": {
"total": 485.57808551000426,
"count": 447,
"self": 180.1857127430858,
"children": {
"TorchPPOOptimizer.update": {
"total": 305.39237276691847,
"count": 22809,
"self": 305.39237276691847
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.030000001075678e-07,
"count": 1,
"self": 9.030000001075678e-07
},
"TrainerController._save_models": {
"total": 0.08280761200057896,
"count": 1,
"self": 0.001353973000732367,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08145363899984659,
"count": 1,
"self": 0.08145363899984659
}
}
}
}
}
}
}