| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.11878236383199692, |
| "min": 0.10809889435768127, |
| "max": 1.2392959594726562, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 3557.769287109375, |
| "min": 3248.155517578125, |
| "max": 37595.28125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989979.0, |
| "min": 29952.0, |
| "max": 989979.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989979.0, |
| "min": 29952.0, |
| "max": 989979.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.0937093123793602, |
| "min": -0.13980858027935028, |
| "max": -0.03965657576918602, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -22.490234375, |
| "min": -33.1346321105957, |
| "max": -9.517578125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.29258492588996887, |
| "min": 0.2259417027235031, |
| "max": 0.48964154720306396, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 70.22038269042969, |
| "min": 54.45195007324219, |
| "max": 117.51396942138672, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0701524821032039, |
| "min": 0.06535336099897435, |
| "max": 0.07161272738445458, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9821347494448547, |
| "min": 0.5008668755187824, |
| "max": 0.9821347494448547, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0005013788562184888, |
| "min": 0.000373782523542247, |
| "max": 0.008696133524944761, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.007019303987058843, |
| "min": 0.004859172806049211, |
| "max": 0.06087293467461333, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.347826122185713e-06, |
| "min": 7.347826122185713e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010286956571059998, |
| "min": 0.00010286956571059998, |
| "max": 0.0031375841541387, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10244924285714285, |
| "min": 0.10244924285714285, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4342894, |
| "min": 1.3691136000000002, |
| "max": 2.3458613, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025467936142857143, |
| "min": 0.00025467936142857143, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035655110599999997, |
| "min": 0.0035655110599999997, |
| "max": 0.10461154386999999, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.2888457477092743, |
| "min": 0.179472878575325, |
| "max": 0.5697922110557556, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 4.043840408325195, |
| "min": 2.153674602508545, |
| "max": 4.191043376922607, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 999.0, |
| "min": 928.0, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 27972.0, |
| "min": 15984.0, |
| "max": 32726.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.9996500518172979, |
| "min": -1.0000000521540642, |
| "max": -0.6978154314252046, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -27.990201450884342, |
| "min": -32.000001668930054, |
| "max": -16.000000834465027, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.9996500518172979, |
| "min": -1.0000000521540642, |
| "max": -0.6978154314252046, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -27.990201450884342, |
| "min": -32.000001668930054, |
| "max": -16.000000834465027, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 2.846828587885414, |
| "min": 1.9769958045799285, |
| "max": 10.185381253249943, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 79.71120046079159, |
| "min": 56.77791683236137, |
| "max": 162.9661000519991, |
| "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": "1739006243", |
| "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": "2.6.0+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1739008490" |
| }, |
| "total": 2246.997819224, |
| "count": 1, |
| "self": 0.5393444309997903, |
| "children": { |
| "run_training.setup": { |
| "total": 0.024433104999843636, |
| "count": 1, |
| "self": 0.024433104999843636 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2246.4340416880004, |
| "count": 1, |
| "self": 1.5748731400240104, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.960077573000035, |
| "count": 1, |
| "self": 3.960077573000035 |
| }, |
| "TrainerController.advance": { |
| "total": 2240.8027684699764, |
| "count": 62994, |
| "self": 1.6008817979759442, |
| "children": { |
| "env_step": { |
| "total": 1513.275015226022, |
| "count": 62994, |
| "self": 1335.5422932179872, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 176.80688636500167, |
| "count": 62994, |
| "self": 5.35005148505752, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 171.45683487994415, |
| "count": 62540, |
| "self": 171.45683487994415 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.9258356430332242, |
| "count": 62994, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2240.684774630029, |
| "count": 62994, |
| "is_parallel": true, |
| "self": 1032.195184332002, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0068483129998639924, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.004990184000007503, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0018581289998564898, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0018581289998564898 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05441686400013168, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006464980001510412, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000482693000094514, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000482693000094514 |
| }, |
| "communicator.exchange": { |
| "total": 0.051234337999858326, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.051234337999858326 |
| }, |
| "steps_from_proto": { |
| "total": 0.0020533350000278006, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005514749998383195, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001501860000189481, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001501860000189481 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1208.489590298027, |
| "count": 62993, |
| "is_parallel": true, |
| "self": 34.57345123904065, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 25.367545844980214, |
| "count": 62993, |
| "is_parallel": true, |
| "self": 25.367545844980214 |
| }, |
| "communicator.exchange": { |
| "total": 1042.905064199027, |
| "count": 62993, |
| "is_parallel": true, |
| "self": 1042.905064199027 |
| }, |
| "steps_from_proto": { |
| "total": 105.6435290149791, |
| "count": 62993, |
| "is_parallel": true, |
| "self": 21.54192881193353, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 84.10160020304556, |
| "count": 503944, |
| "is_parallel": true, |
| "self": 84.10160020304556 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 725.9268714459783, |
| "count": 62994, |
| "self": 2.6566088199870137, |
| "children": { |
| "process_trajectory": { |
| "total": 139.04254404098697, |
| "count": 62994, |
| "self": 138.7163282629865, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.32621577800046, |
| "count": 2, |
| "self": 0.32621577800046 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 584.2277185850044, |
| "count": 423, |
| "self": 322.1025937070101, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 262.12512487799427, |
| "count": 22842, |
| "self": 262.12512487799427 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0199996722803917e-06, |
| "count": 1, |
| "self": 1.0199996722803917e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0963214850003169, |
| "count": 1, |
| "self": 0.0013519990002350823, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09496948600008182, |
| "count": 1, |
| "self": 0.09496948600008182 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
