ppo-Pyramids / run_logs /timers.json
debisoft's picture
First Push
d91bc93 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3623979985713959,
"min": 0.3623979985713959,
"max": 1.4408321380615234,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10947.318359375,
"min": 10947.318359375,
"max": 43709.08203125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989952.0,
"min": 29895.0,
"max": 989952.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989952.0,
"min": 29895.0,
"max": 989952.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4558170437812805,
"min": -0.12463133782148361,
"max": 0.48110297322273254,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 123.07060241699219,
"min": -30.036151885986328,
"max": 132.30331420898438,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.06688516587018967,
"min": -0.04279056936502457,
"max": 0.3141217827796936,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 18.05899429321289,
"min": -11.767406463623047,
"max": 74.44686126708984,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06765516994415695,
"min": 0.06454814584814696,
"max": 0.07404530558569221,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9471723792181972,
"min": 0.6380696558178148,
"max": 1.0674368462459112,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01671037359864429,
"min": 0.0010059703906849615,
"max": 0.01671037359864429,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23394523038102005,
"min": 0.012071644688219538,
"max": 0.23394523038102005,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.33374755545e-06,
"min": 7.33374755545e-06,
"max": 0.0002946822684392444,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001026724657763,
"min": 0.0001026724657763,
"max": 0.0035079611306796992,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244455,
"min": 0.10244455,
"max": 0.1982274222222222,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4342237,
"min": 1.4342237,
"max": 2.5693203000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025421054500000004,
"min": 0.00025421054500000004,
"max": 0.009822919480000001,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035589476300000008,
"min": 0.0035589476300000008,
"max": 0.11695509797,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011980079114437103,
"min": 0.011980079114437103,
"max": 0.3783128261566162,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16772110760211945,
"min": 0.16772110760211945,
"max": 3.404815435409546,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 411.8904109589041,
"min": 364.35897435897436,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30068.0,
"min": 17333.0,
"max": 33155.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4180891645719875,
"min": -0.9999613423020609,
"max": 1.6177895918682024,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 104.93859817832708,
"min": -30.998801611363888,
"max": 124.56979857385159,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4180891645719875,
"min": -0.9999613423020609,
"max": 1.6177895918682024,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 104.93859817832708,
"min": -30.998801611363888,
"max": 124.56979857385159,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0525054746054544,
"min": 0.047824298113648016,
"max": 7.050449115534623,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.8854051208036253,
"min": 3.590011120220879,
"max": 126.90808407962322,
"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": "1760350692",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760353881"
},
"total": 3188.0562442869996,
"count": 1,
"self": 0.7366037779993349,
"children": {
"run_training.setup": {
"total": 0.05566642099984165,
"count": 1,
"self": 0.05566642099984165
},
"TrainerController.start_learning": {
"total": 3187.2639740880004,
"count": 1,
"self": 2.312681189931027,
"children": {
"TrainerController._reset_env": {
"total": 3.1048068899999635,
"count": 1,
"self": 3.1048068899999635
},
"TrainerController.advance": {
"total": 3181.74454303307,
"count": 63677,
"self": 2.542446480067156,
"children": {
"env_step": {
"total": 2140.9117720670674,
"count": 63677,
"self": 1986.7648449806147,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.75394414878065,
"count": 63677,
"self": 6.916537541928847,
"children": {
"TorchPolicy.evaluate": {
"total": 145.8374066068518,
"count": 62555,
"self": 145.8374066068518
}
}
},
"workers": {
"total": 1.392982937672059,
"count": 63677,
"self": 0.0,
"children": {
"worker_root": {
"total": 3178.7895148659554,
"count": 63677,
"is_parallel": true,
"self": 1373.9788520790153,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002125113000147394,
"count": 1,
"is_parallel": true,
"self": 0.0007225229965115432,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014025900036358507,
"count": 8,
"is_parallel": true,
"self": 0.0014025900036358507
}
}
},
"UnityEnvironment.step": {
"total": 0.07087036000120861,
"count": 1,
"is_parallel": true,
"self": 0.0006756970014976105,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005674479998560855,
"count": 1,
"is_parallel": true,
"self": 0.0005674479998560855
},
"communicator.exchange": {
"total": 0.06743760999961523,
"count": 1,
"is_parallel": true,
"self": 0.06743760999961523
},
"steps_from_proto": {
"total": 0.0021896050002396805,
"count": 1,
"is_parallel": true,
"self": 0.0004099500056327088,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017796549946069717,
"count": 8,
"is_parallel": true,
"self": 0.0017796549946069717
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1804.8106627869402,
"count": 63676,
"is_parallel": true,
"self": 45.876904312817715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 30.2584594290729,
"count": 63676,
"is_parallel": true,
"self": 30.2584594290729
},
"communicator.exchange": {
"total": 1583.111864169081,
"count": 63676,
"is_parallel": true,
"self": 1583.111864169081
},
"steps_from_proto": {
"total": 145.5634348759686,
"count": 63676,
"is_parallel": true,
"self": 29.05790338684892,
"children": {
"_process_rank_one_or_two_observation": {
"total": 116.50553148911968,
"count": 509408,
"is_parallel": true,
"self": 116.50553148911968
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1038.2903244859353,
"count": 63677,
"self": 4.468165189877254,
"children": {
"process_trajectory": {
"total": 157.6194544470618,
"count": 63677,
"self": 157.33005227006288,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28940217699891946,
"count": 2,
"self": 0.28940217699891946
}
}
},
"_update_policy": {
"total": 876.2027048489963,
"count": 456,
"self": 357.9403880730515,
"children": {
"TorchPPOOptimizer.update": {
"total": 518.2623167759448,
"count": 22830,
"self": 518.2623167759448
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1230004020035267e-06,
"count": 1,
"self": 1.1230004020035267e-06
},
"TrainerController._save_models": {
"total": 0.10194185199907224,
"count": 1,
"self": 0.006152269999802229,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09578958199927001,
"count": 1,
"self": 0.09578958199927001
}
}
}
}
}
}
}