| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.1642003357410431, |
| "min": 0.16056354343891144, |
| "max": 1.4807732105255127, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4920.755859375, |
| "min": 4804.06103515625, |
| "max": 44920.734375, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999947.0, |
| "min": 29952.0, |
| "max": 2999947.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999947.0, |
| "min": 29952.0, |
| "max": 2999947.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6865847706794739, |
| "min": -0.1346987932920456, |
| "max": 0.8179547786712646, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 199.10958862304688, |
| "min": -32.32770919799805, |
| "max": 242.81996154785156, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.008287320844829082, |
| "min": -0.04137527570128441, |
| "max": 0.2740214467048645, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.403323173522949, |
| "min": -10.426569938659668, |
| "max": 65.46407318115234, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06797425576951353, |
| "min": 0.06472775858682801, |
| "max": 0.07328293041290852, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9516395807731896, |
| "min": 0.47834217100405546, |
| "max": 1.0798985781558956, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.013280468275687391, |
| "min": 0.0008633737378850455, |
| "max": 0.015937679237963277, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.18592655585962348, |
| "min": 0.010100517988168325, |
| "max": 0.2231275093314859, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4504709451142875e-06, |
| "min": 1.4504709451142875e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.0306593231600025e-05, |
| "min": 2.0306593231600025e-05, |
| "max": 0.003937233687588832, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10048345714285714, |
| "min": 0.10048345714285714, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4067684, |
| "min": 1.3897045333333333, |
| "max": 2.812411166666667, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.8297368571428634e-05, |
| "min": 5.8297368571428634e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008161631600000008, |
| "min": 0.0008161631600000008, |
| "max": 0.13125987555, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.004726450890302658, |
| "min": 0.0044143847189843655, |
| "max": 0.4417647421360016, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.06617031246423721, |
| "min": 0.06180138885974884, |
| "max": 3.092353105545044, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 264.3644859813084, |
| "min": 224.79032258064515, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28287.0, |
| "min": 15984.0, |
| "max": 32082.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7169420439227718, |
| "min": -1.0000000521540642, |
| "max": 1.775209667701875, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 183.7127986997366, |
| "min": -32.000001668930054, |
| "max": 229.11859840154648, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7169420439227718, |
| "min": -1.0000000521540642, |
| "max": 1.775209667701875, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 183.7127986997366, |
| "min": -32.000001668930054, |
| "max": 229.11859840154648, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.013199198651062238, |
| "min": 0.010884598844797673, |
| "max": 9.43246571533382, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.4123142556636594, |
| "min": 1.329719188332092, |
| "max": 150.9194514453411, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1691840274", |
| "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
| "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", |
| "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": "1691847321" |
| }, |
| "total": 7047.049745183001, |
| "count": 1, |
| "self": 1.0374780419997478, |
| "children": { |
| "run_training.setup": { |
| "total": 0.06228860799978975, |
| "count": 1, |
| "self": 0.06228860799978975 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7045.949978533001, |
| "count": 1, |
| "self": 3.8242003819214005, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 4.370690222000121, |
| "count": 1, |
| "self": 4.370690222000121 |
| }, |
| "TrainerController.advance": { |
| "total": 7037.607241682081, |
| "count": 194153, |
| "self": 3.8922108027318245, |
| "children": { |
| "env_step": { |
| "total": 5075.524332072416, |
| "count": 194153, |
| "self": 4763.660695574962, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 309.54089548233947, |
| "count": 194153, |
| "self": 13.776553553249187, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 295.7643419290903, |
| "count": 187553, |
| "self": 295.7643419290903 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.3227410151143886, |
| "count": 194153, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7030.802261830786, |
| "count": 194153, |
| "is_parallel": true, |
| "self": 2605.1339650489035, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0017717289999836794, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005805659998259216, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011911630001577578, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011911630001577578 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04692590700005894, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005581739999342972, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00047111300000324263, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00047111300000324263 |
| }, |
| "communicator.exchange": { |
| "total": 0.044171782000148596, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.044171782000148596 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017248379999728058, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003541170001426508, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001370720999830155, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001370720999830155 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4425.668296781882, |
| "count": 194152, |
| "is_parallel": true, |
| "self": 100.78579607497795, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 66.34427626294041, |
| "count": 194152, |
| "is_parallel": true, |
| "self": 66.34427626294041 |
| }, |
| "communicator.exchange": { |
| "total": 3949.1558300309325, |
| "count": 194152, |
| "is_parallel": true, |
| "self": 3949.1558300309325 |
| }, |
| "steps_from_proto": { |
| "total": 309.382394413032, |
| "count": 194152, |
| "is_parallel": true, |
| "self": 59.938961736002966, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 249.44343267702902, |
| "count": 1553216, |
| "is_parallel": true, |
| "self": 249.44343267702902 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1958.1906988069331, |
| "count": 194153, |
| "self": 7.614389938843942, |
| "children": { |
| "process_trajectory": { |
| "total": 335.4976165240587, |
| "count": 194153, |
| "self": 334.8579583170599, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.6396582069987744, |
| "count": 6, |
| "self": 0.6396582069987744 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1615.0786923440305, |
| "count": 1390, |
| "self": 1056.648241502924, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 558.4304508411064, |
| "count": 68385, |
| "self": 558.4304508411064 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.4689994713990018e-06, |
| "count": 1, |
| "self": 1.4689994713990018e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.14784477799912565, |
| "count": 1, |
| "self": 0.001945748999787611, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.14589902899933804, |
| "count": 1, |
| "self": 0.14589902899933804 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
