ppo-PyramidsRND / run_logs /timers.json
iamnamas's picture
Initial Commit - First Training Run
5ae51a2 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4392603933811188,
"min": 0.4392603933811188,
"max": 1.393212080001831,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13234.037109375,
"min": 13234.037109375,
"max": 42264.48046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989935.0,
"min": 29952.0,
"max": 989935.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989935.0,
"min": 29952.0,
"max": 989935.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5749951601028442,
"min": -0.08994577080011368,
"max": 0.6763888001441956,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 159.27366638183594,
"min": -21.766876220703125,
"max": 192.77081298828125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.030171066522598267,
"min": -0.039545558393001556,
"max": 0.5522091388702393,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.357385635375977,
"min": -10.835482597351074,
"max": 130.87356567382812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06537186194555926,
"min": 0.06494192867068618,
"max": 0.07351574250938779,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9152060672378296,
"min": 0.4832755459105227,
"max": 1.0479814798842804,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014500204739499974,
"min": 0.0011073189678155496,
"max": 0.01766500396220686,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20300286635299963,
"min": 0.007751232774708847,
"max": 0.2649750594331029,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.528168919214287e-06,
"min": 7.528168919214287e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010539436486900002,
"min": 0.00010539436486900002,
"max": 0.0036328222890592995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250935714285714,
"min": 0.10250935714285714,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.435131,
"min": 1.3691136000000002,
"max": 2.6109406999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026068477857142853,
"min": 0.00026068477857142853,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036495868999999997,
"min": 0.0036495868999999997,
"max": 0.12111297592999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010082513093948364,
"min": 0.009733769111335278,
"max": 0.6308965682983398,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1411551833152771,
"min": 0.13627277314662933,
"max": 4.416275978088379,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 306.14285714285717,
"min": 289.3980582524272,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27859.0,
"min": 15984.0,
"max": 33588.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.649887896501101,
"min": -1.0000000521540642,
"max": 1.6884139831364156,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 150.1397985816002,
"min": -32.000001668930054,
"max": 170.27639889717102,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.649887896501101,
"min": -1.0000000521540642,
"max": 1.6884139831364156,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 150.1397985816002,
"min": -32.000001668930054,
"max": 170.27639889717102,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03198979353880162,
"min": 0.02922079418147281,
"max": 13.21890873182565,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.911071212030947,
"min": 2.911071212030947,
"max": 211.5025397092104,
"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": "1759404456",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/namas/anaconda3/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --width=1024 --height=768",
"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": "1759405211"
},
"total": 755.3766928279947,
"count": 1,
"self": 0.21738899796037003,
"children": {
"run_training.setup": {
"total": 0.01916261701262556,
"count": 1,
"self": 0.01916261701262556
},
"TrainerController.start_learning": {
"total": 755.1401412130217,
"count": 1,
"self": 0.5765031295013614,
"children": {
"TrainerController._reset_env": {
"total": 4.270191418007016,
"count": 1,
"self": 4.270191418007016
},
"TrainerController.advance": {
"total": 750.2566556695092,
"count": 64090,
"self": 0.50957226078026,
"children": {
"env_step": {
"total": 506.28077811104595,
"count": 64090,
"self": 451.22849824861623,
"children": {
"SubprocessEnvManager._take_step": {
"total": 54.65378727094503,
"count": 64090,
"self": 1.6756841824389994,
"children": {
"TorchPolicy.evaluate": {
"total": 52.97810308850603,
"count": 62558,
"self": 52.97810308850603
}
}
},
"workers": {
"total": 0.39849259148468263,
"count": 64090,
"self": 0.0,
"children": {
"worker_root": {
"total": 754.3419028247008,
"count": 64090,
"is_parallel": true,
"self": 344.4919027207361,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010975929908454418,
"count": 1,
"is_parallel": true,
"self": 0.00028179402579553425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008157989650499076,
"count": 8,
"is_parallel": true,
"self": 0.0008157989650499076
}
}
},
"UnityEnvironment.step": {
"total": 0.016073942999355495,
"count": 1,
"is_parallel": true,
"self": 0.00022878299932926893,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002006209979299456,
"count": 1,
"is_parallel": true,
"self": 0.0002006209979299456
},
"communicator.exchange": {
"total": 0.015100375982001424,
"count": 1,
"is_parallel": true,
"self": 0.015100375982001424
},
"steps_from_proto": {
"total": 0.0005441630200948566,
"count": 1,
"is_parallel": true,
"self": 0.0001222220598720014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004219409602228552,
"count": 8,
"is_parallel": true,
"self": 0.0004219409602228552
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 409.8500001039647,
"count": 64089,
"is_parallel": true,
"self": 8.698886009980924,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.996967378043337,
"count": 64089,
"is_parallel": true,
"self": 5.996967378043337
},
"communicator.exchange": {
"total": 372.1939030549256,
"count": 64089,
"is_parallel": true,
"self": 372.1939030549256
},
"steps_from_proto": {
"total": 22.96024366101483,
"count": 64089,
"is_parallel": true,
"self": 4.881209718150785,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.079033942864044,
"count": 512712,
"is_parallel": true,
"self": 18.079033942864044
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 243.466305297683,
"count": 64090,
"self": 1.1873920980433468,
"children": {
"process_trajectory": {
"total": 53.82319737243233,
"count": 64090,
"self": 53.7353419274441,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08785544498823583,
"count": 2,
"self": 0.08785544498823583
}
}
},
"_update_policy": {
"total": 188.4557158272073,
"count": 453,
"self": 108.2818609510432,
"children": {
"TorchPPOOptimizer.update": {
"total": 80.17385487616411,
"count": 22797,
"self": 80.17385487616411
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.7101639211177826e-07,
"count": 1,
"self": 4.7101639211177826e-07
},
"TrainerController._save_models": {
"total": 0.03679052498773672,
"count": 1,
"self": 0.0008377920021302998,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03595273298560642,
"count": 1,
"self": 0.03595273298560642
}
}
}
}
}
}
}