| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.20050130784511566, |
| "min": 0.19169797003269196, |
| "max": 0.2917623221874237, |
| "count": 34 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 6040.70361328125, |
| "min": 3002.727783203125, |
| "max": 8827.560546875, |
| "count": 34 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 241.7642276422764, |
| "min": 211.975, |
| "max": 312.6774193548387, |
| "count": 34 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29737.0, |
| "min": 8479.0, |
| "max": 32058.0, |
| "count": 34 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999957.0, |
| "min": 2009987.0, |
| "max": 2999957.0, |
| "count": 34 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999957.0, |
| "min": 2009987.0, |
| "max": 2999957.0, |
| "count": 34 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7713999152183533, |
| "min": 0.6358982920646667, |
| "max": 0.7892741560935974, |
| "count": 34 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 225.248779296875, |
| "min": 59.13854217529297, |
| "max": 233.15284729003906, |
| "count": 34 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.005710362922400236, |
| "min": 0.005461862310767174, |
| "max": 0.026293151080608368, |
| "count": 34 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.6674259901046753, |
| "min": 1.3461965322494507, |
| "max": 7.756479740142822, |
| "count": 34 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7591774031039207, |
| "min": 1.6012687989140069, |
| "max": 1.7865384488533704, |
| "count": 34 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 218.13799798488617, |
| "min": 69.67499950528145, |
| "max": 231.0405979603529, |
| "count": 34 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7591774031039207, |
| "min": 1.6012687989140069, |
| "max": 1.7865384488533704, |
| "count": 34 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 218.13799798488617, |
| "min": 69.67499950528145, |
| "max": 231.0405979603529, |
| "count": 34 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.010398394694998241, |
| "min": 0.010362799834789863, |
| "max": 0.01481215390745689, |
| "count": 34 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.2894009421797819, |
| "min": 0.44559615731122904, |
| "max": 1.5044092741591157, |
| "count": 34 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 34 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 34 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06910448090056888, |
| "min": 0.06701293528264311, |
| "max": 0.07417189808620606, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.20731344270170665, |
| "min": 0.13631293868093053, |
| "max": 0.22251569425861817, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01524706046572343, |
| "min": 0.012566591292367472, |
| "max": 0.016535253958621373, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.04574118139717029, |
| "min": 0.026997257619223093, |
| "max": 0.049605761875864116, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.06169964613334e-06, |
| "min": 1.06169964613334e-06, |
| "max": 9.793286735573332e-05, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 3.18509893840002e-06, |
| "min": 3.18509893840002e-06, |
| "max": 0.0002937986020672, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10035386666666668, |
| "min": 0.10035386666666668, |
| "max": 0.13264426666666665, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 0.30106160000000004, |
| "min": 0.2210010666666667, |
| "max": 0.3979328, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 4.535128000000024e-05, |
| "min": 4.535128000000024e-05, |
| "max": 0.00327116224, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00013605384000000073, |
| "min": 0.00013605384000000073, |
| "max": 0.00981348672, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.00416584312915802, |
| "min": 0.0040358733385801315, |
| "max": 0.004870005417615175, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.01249752938747406, |
| "min": 0.00846722163259983, |
| "max": 0.014610015787184238, |
| "count": 33 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1683880154", |
| "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 --resume", |
| "mlagents_version": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1683882939" |
| }, |
| "total": 2784.2696735679992, |
| "count": 1, |
| "self": 0.5446636629994828, |
| "children": { |
| "run_training.setup": { |
| "total": 0.03739161499925103, |
| "count": 1, |
| "self": 0.03739161499925103 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2783.6876182900005, |
| "count": 1, |
| "self": 1.5056411250634483, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.8262678279998, |
| "count": 1, |
| "self": 3.8262678279998 |
| }, |
| "TrainerController.advance": { |
| "total": 2778.167793399937, |
| "count": 65503, |
| "self": 1.4492462506814263, |
| "children": { |
| "env_step": { |
| "total": 1882.3800309799626, |
| "count": 65503, |
| "self": 1765.581686727819, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 115.96026929217987, |
| "count": 65503, |
| "self": 4.755355206159948, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 111.20491408601993, |
| "count": 62569, |
| "self": 111.20491408601993 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8380749599637056, |
| "count": 65503, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2778.0892850379496, |
| "count": 65503, |
| "is_parallel": true, |
| "self": 1126.8145868987158, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.001663746000303945, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005226020002737641, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001141144000030181, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001141144000030181 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04883291499936604, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006346179989122902, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00046008200024516555, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00046008200024516555 |
| }, |
| "communicator.exchange": { |
| "total": 0.04573440599961032, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04573440599961032 |
| }, |
| "steps_from_proto": { |
| "total": 0.0020038090005982667, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00042162400222878205, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015821849983694847, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015821849983694847 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1651.2746981392338, |
| "count": 65502, |
| "is_parallel": true, |
| "self": 31.880492302464518, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.42365856122433, |
| "count": 65502, |
| "is_parallel": true, |
| "self": 22.42365856122433 |
| }, |
| "communicator.exchange": { |
| "total": 1498.6431749411222, |
| "count": 65502, |
| "is_parallel": true, |
| "self": 1498.6431749411222 |
| }, |
| "steps_from_proto": { |
| "total": 98.32737233442276, |
| "count": 65502, |
| "is_parallel": true, |
| "self": 20.24562789644824, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 78.08174443797452, |
| "count": 524016, |
| "is_parallel": true, |
| "self": 78.08174443797452 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 894.3385161692931, |
| "count": 65503, |
| "self": 2.7951120823527162, |
| "children": { |
| "process_trajectory": { |
| "total": 117.07126433492886, |
| "count": 65503, |
| "self": 116.70099271292747, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.37027162200138264, |
| "count": 2, |
| "self": 0.37027162200138264 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 774.4721397520116, |
| "count": 97, |
| "self": 469.8033551721992, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 304.6687845798124, |
| "count": 31056, |
| "self": 304.6687845798124 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0660005500540137e-06, |
| "count": 1, |
| "self": 1.0660005500540137e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.18791487099952064, |
| "count": 1, |
| "self": 0.004501023000557325, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.18341384799896332, |
| "count": 1, |
| "self": 0.18341384799896332 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
