ppo-PyramidsRND / run_logs /timers.json
heesup's picture
First Push
d88aeb3 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.8103523850440979,
"min": 0.8103523850440979,
"max": 1.481785535812378,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 24038.29296875,
"min": 24038.29296875,
"max": 44951.4453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.08681991696357727,
"min": -0.11447757482528687,
"max": 0.1185968890786171,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 21.704978942871094,
"min": -27.589096069335938,
"max": 29.886415481567383,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0291525200009346,
"min": 0.009507951326668262,
"max": 0.27285289764404297,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.288129806518555,
"min": 2.3674798011779785,
"max": 64.6661376953125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06830410407589796,
"min": 0.06484350233221403,
"max": 0.07301550749250747,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0245615611384693,
"min": 0.5109379460908682,
"max": 1.0245615611384693,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.007382124040422615,
"min": 0.0001509703851398303,
"max": 0.008754605951658395,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.11073186060633923,
"min": 0.002113585391957624,
"max": 0.12256448332321752,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.482557505846666e-06,
"min": 7.482557505846666e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011223836258769998,
"min": 0.00011223836258769998,
"max": 0.0033819026726991997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249415333333335,
"min": 0.10249415333333335,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374123000000002,
"min": 1.3886848,
"max": 2.5273008000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002591659180000001,
"min": 0.0002591659180000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003887488770000001,
"min": 0.003887488770000001,
"max": 0.11275734992000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009230995550751686,
"min": 0.009230995550751686,
"max": 0.40759310126304626,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13846492767333984,
"min": 0.13191238045692444,
"max": 2.853151798248291,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 755.3170731707318,
"min": 748.125,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30968.0,
"min": 15984.0,
"max": 32568.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.41517069935798645,
"min": -1.0000000521540642,
"max": 0.46630240286268837,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 17.021998673677444,
"min": -31.99480165541172,
"max": 19.118398517370224,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.41517069935798645,
"min": -1.0000000521540642,
"max": 0.46630240286268837,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 17.021998673677444,
"min": -31.99480165541172,
"max": 19.118398517370224,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0724311224667628,
"min": 0.0724311224667628,
"max": 8.176845656707883,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.969676021137275,
"min": 2.910837574105244,
"max": 130.82953050732613,
"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": "1764200332",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/lion397@ad3.ucdavis.edu/miniforge3/envs/py310/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": "1764202539"
},
"total": 2207.56190684624,
"count": 1,
"self": 0.4728108197450638,
"children": {
"run_training.setup": {
"total": 0.02949627861380577,
"count": 1,
"self": 0.02949627861380577
},
"TrainerController.start_learning": {
"total": 2207.0595997478813,
"count": 1,
"self": 1.7453499790281057,
"children": {
"TrainerController._reset_env": {
"total": 2.7883310094475746,
"count": 1,
"self": 2.7883310094475746
},
"TrainerController.advance": {
"total": 2202.395910134539,
"count": 63211,
"self": 1.7691988181322813,
"children": {
"env_step": {
"total": 1095.1240665055811,
"count": 63211,
"self": 864.6430133320391,
"children": {
"SubprocessEnvManager._take_step": {
"total": 229.4306788034737,
"count": 63211,
"self": 5.444724146276712,
"children": {
"TorchPolicy.evaluate": {
"total": 223.985954657197,
"count": 62551,
"self": 223.985954657197
}
}
},
"workers": {
"total": 1.0503743700683117,
"count": 63211,
"self": 0.0,
"children": {
"worker_root": {
"total": 2204.6527202855796,
"count": 63211,
"is_parallel": true,
"self": 1463.561967657879,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001743663102388382,
"count": 1,
"is_parallel": true,
"self": 0.0005436204373836517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012000426650047302,
"count": 8,
"is_parallel": true,
"self": 0.0012000426650047302
}
}
},
"UnityEnvironment.step": {
"total": 0.03975217416882515,
"count": 1,
"is_parallel": true,
"self": 0.0003789477050304413,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042678602039813995,
"count": 1,
"is_parallel": true,
"self": 0.00042678602039813995
},
"communicator.exchange": {
"total": 0.03770072944462299,
"count": 1,
"is_parallel": true,
"self": 0.03770072944462299
},
"steps_from_proto": {
"total": 0.0012457109987735748,
"count": 1,
"is_parallel": true,
"self": 0.0003333352506160736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009123757481575012,
"count": 8,
"is_parallel": true,
"self": 0.0009123757481575012
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 741.0907526277006,
"count": 63210,
"is_parallel": true,
"self": 22.71052259206772,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.430144572630525,
"count": 63210,
"is_parallel": true,
"self": 24.430144572630525
},
"communicator.exchange": {
"total": 618.6869182959199,
"count": 63210,
"is_parallel": true,
"self": 618.6869182959199
},
"steps_from_proto": {
"total": 75.26316716708243,
"count": 63210,
"is_parallel": true,
"self": 19.48693180270493,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.7762353643775,
"count": 505680,
"is_parallel": true,
"self": 55.7762353643775
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1105.5026448108256,
"count": 63211,
"self": 3.0268058627843857,
"children": {
"process_trajectory": {
"total": 144.81732693500817,
"count": 63211,
"self": 144.5397399161011,
"children": {
"RLTrainer._checkpoint": {
"total": 0.27758701890707016,
"count": 2,
"self": 0.27758701890707016
}
}
},
"_update_policy": {
"total": 957.658512013033,
"count": 447,
"self": 447.9687806032598,
"children": {
"TorchPPOOptimizer.update": {
"total": 509.68973140977323,
"count": 22770,
"self": 509.68973140977323
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.305954694747925e-06,
"count": 1,
"self": 2.305954694747925e-06
},
"TrainerController._save_models": {
"total": 0.13000631891191006,
"count": 1,
"self": 0.001277770847082138,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12872854806482792,
"count": 1,
"self": 0.12872854806482792
}
}
}
}
}
}
}