Hugdir/Pyramids-PPO-RND-Success
069
1{2 "name": "root",3 "gauges": {4 "Pyramids.Policy.Entropy.mean": {5 "value": 0.23843881487846375,6 "min": 0.23753118515014648,7 "max": 1.4292476177215576,8 "count": 529 },10 "Pyramids.Policy.Entropy.sum": {11 "value": 7134.08935546875,12 "min": 7038.52392578125,13 "max": 43357.65625,14 "count": 5215 },16 "Pyramids.Step.mean": {17 "value": 1559896.0,18 "min": 29952.0,19 "max": 1559896.0,20 "count": 5221 },22 "Pyramids.Step.sum": {23 "value": 1559896.0,24 "min": 29952.0,25 "max": 1559896.0,26 "count": 5227 },28 "Pyramids.Policy.ExtrinsicValueEstimate.mean": {29 "value": 0.8326560258865356,30 "min": -0.09205543994903564,31 "max": 0.8420236706733704,32 "count": 5233 },34 "Pyramids.Policy.ExtrinsicValueEstimate.sum": {35 "value": 248.13150024414062,36 "min": -22.185361862182617,37 "max": 257.65924072265625,38 "count": 5239 },40 "Pyramids.Policy.RndValueEstimate.mean": {41 "value": 0.010321666486561298,42 "min": -0.00941386166960001,43 "max": 0.30597904324531555,44 "count": 5245 },46 "Pyramids.Policy.RndValueEstimate.sum": {47 "value": 3.0758566856384277,48 "min": -2.607639789581299,49 "max": 73.74095153808594,50 "count": 5251 },52 "Pyramids.Losses.PolicyLoss.mean": {53 "value": 0.07147382796156357,54 "min": 0.06486261799195224,55 "max": 0.07377905931142677,56 "count": 5257 },58 "Pyramids.Losses.PolicyLoss.sum": {59 "value": 1.00063359146189,60 "min": 0.48229706238743836,61 "max": 1.1066858896714016,62 "count": 5263 },64 "Pyramids.Losses.ValueLoss.mean": {65 "value": 0.01327213931332097,66 "min": 0.00015669237809535664,67 "max": 0.0166132790467921,68 "count": 5269 },70 "Pyramids.Losses.ValueLoss.sum": {71 "value": 0.1858099503864936,72 "min": 0.0020370009152396364,73 "max": 0.2491991857018815,74 "count": 5275 },76 "Pyramids.Policy.LearningRate.mean": {77 "value": 0.00014549105864585473,78 "min": 0.00014549105864585473,79 "max": 0.00029838354339596195,80 "count": 5281 },82 "Pyramids.Policy.LearningRate.sum": {83 "value": 0.0020368748210419663,84 "min": 0.0020368748210419663,85 "max": 0.004027387257537632,86 "count": 5287 },88 "Pyramids.Policy.Epsilon.mean": {89 "value": 0.1484970023809524,90 "min": 0.1484970023809524,91 "max": 0.19946118095238097,92 "count": 5293 },94 "Pyramids.Policy.Epsilon.sum": {95 "value": 2.0789580333333335,96 "min": 1.3962282666666668,97 "max": 2.842462366666667,98 "count": 5299 },100 "Pyramids.Policy.Beta.mean": {101 "value": 0.004854850537857143,102 "min": 0.004854850537857143,103 "max": 0.009946171977142856,104 "count": 52105 },106 "Pyramids.Policy.Beta.sum": {107 "value": 0.06796790753000001,108 "min": 0.06796790753000001,109 "max": 0.13426199043,110 "count": 52111 },112 "Pyramids.Losses.RNDLoss.mean": {113 "value": 0.01016409695148468,114 "min": 0.009826130233705044,115 "max": 0.469675749540329,116 "count": 52117 },118 "Pyramids.Losses.RNDLoss.sum": {119 "value": 0.14229735732078552,120 "min": 0.13936378061771393,121 "max": 3.2877302169799805,122 "count": 52123 },124 "Pyramids.Environment.EpisodeLength.mean": {125 "value": 230.04724409448818,126 "min": 220.32575757575756,127 "max": 999.0,128 "count": 52129 },130 "Pyramids.Environment.EpisodeLength.sum": {131 "value": 29216.0,132 "min": 15984.0,133 "max": 32708.0,134 "count": 52135 },136 "Pyramids.Environment.CumulativeReward.mean": {137 "value": 1.7541999853267445,138 "min": -1.0000000521540642,139 "max": 1.7697099173114499,140 "count": 52141 },142 "Pyramids.Environment.CumulativeReward.sum": {143 "value": 222.78339813649654,144 "min": -30.99380160868168,145 "max": 235.2053981423378,146 "count": 52147 },148 "Pyramids.Policy.ExtrinsicReward.mean": {149 "value": 1.7541999853267445,150 "min": -1.0000000521540642,151 "max": 1.7697099173114499,152 "count": 52153 },154 "Pyramids.Policy.ExtrinsicReward.sum": {155 "value": 222.78339813649654,156 "min": -30.99380160868168,157 "max": 235.2053981423378,158 "count": 52159 },160 "Pyramids.Policy.RndReward.mean": {161 "value": 0.024360329406096472,162 "min": 0.023964540308591544,163 "max": 9.351730020716786,164 "count": 52165 },166 "Pyramids.Policy.RndReward.sum": {167 "value": 3.093761834574252,168 "min": 3.08454118440568,169 "max": 149.62768033146858,170 "count": 52171 },172 "Pyramids.IsTraining.mean": {173 "value": 1.0,174 "min": 1.0,175 "max": 1.0,176 "count": 52177 },178 "Pyramids.IsTraining.sum": {179 "value": 1.0,180 "min": 1.0,181 "max": 1.0,182 "count": 52183 }184 },185 "metadata": {186 "timer_format_version": "0.1.0",187 "start_time_seconds": "1790469955",188 "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",189 "command_line_arguments": "/usr/local/miniconda/envs/mlagents/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",190 "mlagents_version": "1.2.0.dev0",191 "mlagents_envs_version": "1.2.0.dev0",192 "communication_protocol_version": "1.5.0",193 "pytorch_version": "2.8.0+cu128",194 "numpy_version": "1.23.5",195 "end_time_seconds": "1790473716"196 },197 "total": 3761.398091067,198 "count": 1,199 "self": 0.4592522090001694,200 "children": {201 "run_training.setup": {202 "total": 0.022923066999965158,203 "count": 1,204 "self": 0.022923066999965158205 },206 "TrainerController.start_learning": {207 "total": 3760.9159157910003,208 "count": 1,209 "self": 1.9284425549435582,210 "children": {211 "TrainerController._reset_env": {212 "total": 3.4518364200000633,213 "count": 1,214 "self": 3.4518364200000633215 },216 "TrainerController.advance": {217 "total": 3755.3513909860562,218 "count": 101305,219 "self": 2.0638578332041106,220 "children": {221 "env_step": {222 "total": 2801.4038006209926,223 "count": 101305,224 "self": 2577.6385888391824,225 "children": {226 "SubprocessEnvManager._take_step": {227 "total": 222.5810634649638,228 "count": 101305,229 "self": 7.046059270903925,230 "children": {231 "TorchPolicy.evaluate": {232 "total": 215.53500419405987,233 "count": 98044,234 "self": 215.53500419405987235 }236 }237 },238 "workers": {239 "total": 1.1841483168466311,240 "count": 101304,241 "self": 0.0,242 "children": {243 "worker_root": {244 "total": 3751.5966338229764,245 "count": 101304,246 "is_parallel": true,247 "self": 1349.8627890279322,248 "children": {249 "run_training.setup": {250 "total": 0.0,251 "count": 0,252 "is_parallel": true,253 "self": 0.0,254 "children": {255 "steps_from_proto": {256 "total": 0.004818004000071596,257 "count": 1,258 "is_parallel": true,259 "self": 0.0035155789994405495,260 "children": {261 "_process_rank_one_or_two_observation": {262 "total": 0.0013024250006310467,263 "count": 8,264 "is_parallel": true,265 "self": 0.0013024250006310467266 }267 }268 },269 "UnityEnvironment.step": {270 "total": 0.05150600199999644,271 "count": 1,272 "is_parallel": true,273 "self": 0.0006052000001091073,274 "children": {275 "UnityEnvironment._generate_step_input": {276 "total": 0.0005078389999653155,277 "count": 1,278 "is_parallel": true,279 "self": 0.0005078389999653155280 },281 "communicator.exchange": {282 "total": 0.04876108500002374,283 "count": 1,284 "is_parallel": true,285 "self": 0.04876108500002374286 },287 "steps_from_proto": {288 "total": 0.001631877999898279,289 "count": 1,290 "is_parallel": true,291 "self": 0.0003466269997716154,292 "children": {293 "_process_rank_one_or_two_observation": {294 "total": 0.0012852510001266637,295 "count": 8,296 "is_parallel": true,297 "self": 0.0012852510001266637298 }299 }300 }301 }302 }303 }304 },305 "UnityEnvironment.step": {306 "total": 2401.733844795044,307 "count": 101303,308 "is_parallel": true,309 "self": 52.23696876606664,310 "children": {311 "UnityEnvironment._generate_step_input": {312 "total": 34.62122753802191,313 "count": 101303,314 "is_parallel": true,315 "self": 34.62122753802191316 },317 "communicator.exchange": {318 "total": 2149.950263898044,319 "count": 101303,320 "is_parallel": true,321 "self": 2149.950263898044322 },323 "steps_from_proto": {324 "total": 164.92538459291177,325 "count": 101303,326 "is_parallel": true,327 "self": 34.348601567288824,328 "children": {329 "_process_rank_one_or_two_observation": {330 "total": 130.57678302562294,331 "count": 810424,332 "is_parallel": true,333 "self": 130.57678302562294334 }335 }336 }337 }338 }339 }340 }341 }342 }343 }344 },345 "trainer_advance": {346 "total": 951.8837325318596,347 "count": 101304,348 "self": 3.8505665268289704,349 "children": {350 "process_trajectory": {351 "total": 173.1932540710327,352 "count": 101304,353 "self": 172.84371863903243,354 "children": {355 "RLTrainer._checkpoint": {356 "total": 0.34953543200026616,357 "count": 3,358 "self": 0.34953543200026616359 }360 }361 },362 "_update_policy": {363 "total": 774.8399119339979,364 "count": 721,365 "self": 413.7242994168921,366 "children": {367 "TorchPPOOptimizer.update": {368 "total": 361.1156125171058,369 "count": 35757,370 "self": 361.1156125171058371 }372 }373 }374 }375 }376 }377 },378 "trainer_threads": {379 "total": 1.4269999155658297e-06,380 "count": 1,381 "self": 1.4269999155658297e-06382 },383 "TrainerController._save_models": {384 "total": 0.1842444030007755,385 "count": 1,386 "self": 0.0015035500009616953,387 "children": {388 "RLTrainer._checkpoint": {389 "total": 0.1827408529998138,390 "count": 1,391 "self": 0.1827408529998138392 }393 }394 }395 }396 }397 }398}