|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.29085955023765564, |
|
"min": 0.27771326899528503, |
|
"max": 1.4358659982681274, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8683.90234375, |
|
"min": 8260.3037109375, |
|
"max": 43558.4296875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989942.0, |
|
"min": 29952.0, |
|
"max": 989942.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989942.0, |
|
"min": 29952.0, |
|
"max": 989942.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6580008864402771, |
|
"min": -0.10523167252540588, |
|
"max": 0.6881210803985596, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 190.16226196289062, |
|
"min": -25.466064453125, |
|
"max": 199.55511474609375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.003299497067928314, |
|
"min": -0.01956799626350403, |
|
"max": 0.35541126132011414, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -0.953554630279541, |
|
"min": -5.479038715362549, |
|
"max": 84.23246765136719, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06842542209542493, |
|
"min": 0.06551635656403118, |
|
"max": 0.07535043190065797, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9579559093359491, |
|
"min": 0.48438851770291896, |
|
"max": 1.0549060466092117, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0170882563734853, |
|
"min": 0.0003243597904036315, |
|
"max": 0.01781443451418403, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2392355892287942, |
|
"min": 0.00421667727524721, |
|
"max": 0.24940208319857643, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.588297470599997e-06, |
|
"min": 7.588297470599997e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010623616458839996, |
|
"min": 0.00010623616458839996, |
|
"max": 0.0035083424305525994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10252939999999999, |
|
"min": 0.10252939999999999, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4354116, |
|
"min": 1.3886848, |
|
"max": 2.5724913999999997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026268706, |
|
"min": 0.00026268706, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036776188399999994, |
|
"min": 0.0036776188399999994, |
|
"max": 0.11696779526000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01337068434804678, |
|
"min": 0.01287037879228592, |
|
"max": 0.38796278834342957, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.18718957901000977, |
|
"min": 0.18018530309200287, |
|
"max": 2.7157394886016846, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 293.3398058252427, |
|
"min": 293.3398058252427, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30214.0, |
|
"min": 15984.0, |
|
"max": 32851.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6814538260491996, |
|
"min": -1.0000000521540642, |
|
"max": 1.6847259858250618, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 174.87119790911674, |
|
"min": -30.99720160663128, |
|
"max": 174.87119790911674, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6814538260491996, |
|
"min": -1.0000000521540642, |
|
"max": 1.6847259858250618, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 174.87119790911674, |
|
"min": -30.99720160663128, |
|
"max": 174.87119790911674, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.041040607013760916, |
|
"min": 0.041040607013760916, |
|
"max": 7.6360088819637895, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.268223129431135, |
|
"min": 3.9343486771686003, |
|
"max": 122.17614211142063, |
|
"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": "1676359438", |
|
"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=PyramidsTraining1 --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": "1676361685" |
|
}, |
|
"total": 2247.1051293530004, |
|
"count": 1, |
|
"self": 0.5244767100002719, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11052963800011639, |
|
"count": 1, |
|
"self": 0.11052963800011639 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2246.470123005, |
|
"count": 1, |
|
"self": 1.2862895390558151, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.1232526470002995, |
|
"count": 1, |
|
"self": 6.1232526470002995 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2238.978154888944, |
|
"count": 64120, |
|
"self": 1.333442772957369, |
|
"children": { |
|
"env_step": { |
|
"total": 1510.3912829679002, |
|
"count": 64120, |
|
"self": 1400.0294468998877, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 109.58598691598718, |
|
"count": 64120, |
|
"self": 4.424752846965475, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 105.1612340690217, |
|
"count": 62547, |
|
"self": 35.31738503210954, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 69.84384903691216, |
|
"count": 62547, |
|
"self": 69.84384903691216 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7758491520253301, |
|
"count": 64120, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2241.6175169840217, |
|
"count": 64120, |
|
"is_parallel": true, |
|
"self": 952.3154244469797, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017961430003197165, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006271430006563605, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001168999999663356, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001168999999663356 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04592267999987598, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005059459999756655, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004652779998650658, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004652779998650658 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04328011500001594, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04328011500001594 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016713410000193107, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004242680001880217, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001247072999831289, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001247072999831289 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1289.302092537042, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 30.996537674081992, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.161050569997315, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 22.161050569997315 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1138.1342664519125, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 1138.1342664519125 |
|
}, |
|
"steps_from_proto": { |
|
"total": 98.01023784105018, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 21.47436004669862, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 76.53587779435156, |
|
"count": 512952, |
|
"is_parallel": true, |
|
"self": 76.53587779435156 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 727.2534291480865, |
|
"count": 64120, |
|
"self": 2.4514008419464517, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 160.9612999581409, |
|
"count": 64120, |
|
"self": 160.78012017714127, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.18117978099962784, |
|
"count": 2, |
|
"self": 0.18117978099962784 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 563.8407283479992, |
|
"count": 456, |
|
"self": 216.39021967506096, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 347.4505086729382, |
|
"count": 22761, |
|
"self": 347.4505086729382 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.950000847107731e-07, |
|
"count": 1, |
|
"self": 8.950000847107731e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08242503499968734, |
|
"count": 1, |
|
"self": 0.001335611999820685, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08108942299986666, |
|
"count": 1, |
|
"self": 0.08108942299986666 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |