Denys88/rl_games

Issues

• SACPlayer deterministic mixup

  #289 opened 13 days ago by llinauer
  1

• minibatch_size_per_env bug ?

  #286 opened 11 days ago by Yougo-robotics
  2

• Difference between network and model

  #283 opened 2 months ago by kaijieshi7
  1

• How does the a2c network rescale the range of the action to [-1,1]

  #285 opened 2 months ago by des-zhong
  3

• How can I export a trained neural network?

  #266 opened 7 months ago by jheyeo222
  5

• Discrete and Continuous

  #282 opened 3 months ago by mxllc
  0

• Normalization implementation is actually computing standardization

  #281 opened 3 months ago by anishhdiwan
  2

• missing python 3.11 support

  #280 opened 3 months ago by igozali
  3

• question about central value

  #279 opened 3 months ago by JoseBarreiros-TRI
  1

• Which version has this '.model_builder.model_factory.register_builder'

  #278 opened 3 months ago by dccdcc7
  0

• question about init_dones tensor in a2c_common

  #277 opened 4 months ago by WSYANGSX
  0

• Adding categorical cross_entropy loss to yaml config.

  #276 opened 4 months ago by Eirikalb
  1

• Getting error while testing

  #262 opened 7 months ago by qureshinomaan
  4

• print_statistics() output of ContinuousA2CBase() might be wrong due to frame update implementation?

  #275 opened 4 months ago by yutaizhou
  0

• How to understand the swap_and_flattern01() operation

  #274 opened 4 months ago by BadWomanY
  1

• How to specify the GPU that loads the model weights when applying to IsaacGym

  #268 opened 6 months ago by Charlie0257
  2

• Requesting docs for rl_games

  #271 opened 5 months ago by anishhdiwan
  1

• How to Correctly Integrate LSTM or GRU into the SAC Algorithm

  #270 opened 6 months ago by namjiwon1023
  1

• How to use Isaac trained customized models (different number of observations and outputs)

  #269 opened 6 months ago by DannyChen1994
  1

• Exporting Dofbot Policy to Onnx From Omni Isaac Gym

  #226 opened a year ago by DJT777
  23

• Is there any plans to move to gymnasium?

  #261 opened 8 months ago by Mayankm96
  2

• Possibility of including Multi Agent Reinforcement Learning

  #248 opened 7 months ago by berttggg
  1

• MultiDiscrete action_mask cannot run

  #264 opened 7 months ago by xialuanshi
  3

• Infer trained neural network manually

  #256 opened 7 months ago by BaranAugustus
  1

• Is there any description of the structure of this package?

  #255 opened 9 months ago by 3505473356
  3

• AttributeError: 'dict' object has no attribute 'clone' in SAC algorithm

  #263 opened 7 months ago by scxzhchacker
  2

• loading checkpoint doesn't work for resuming training and test

  #247 opened a year ago by qiuyuchen14
  9

• Bounds / regularisation loss and action clipping

  #257 opened 9 months ago by johannespitz
  2

• When to use Model or Network?

  #252 opened 9 months ago by HGGshiwo
  1

• Possibilities to use pointcloud as input for the SAC

  #249 opened 9 months ago by robinvetsch
  1

• Implementation and performance questions

  #228 opened 10 months ago by mmcaulif
  1

• advantage in a2c_common

  #250 opened 10 months ago by mxllc
  1

• Is Regularizer option working ?

  #245 opened a year ago by arminvburren
  1

• Externally Load Checkpoint

  #243 opened a year ago by davesarmoury
  10

• Question about value_bootstrap

  #242 opened a year ago by johannespitz
  4

• Bug in network_buider

  #241 opened a year ago by xuanyaoming
  5

• MAPPO with isaac gym

  #234 opened a year ago by Asad-Shahid
  2

• How to implement a new RL algorithm?

  #239 opened a year ago by xuanyaoming
  4

• what is self.mb_rnn_states

  #207 opened a year ago by 1tac11
  1

• Checkpoint when using SAC

  #237 opened a year ago by Baerenstark2
  1

• rl_device in Network

  #206 opened 2 years ago by 1tac11
  2

• self.minibatch_size

  #232 opened a year ago by 1tac11
  9

• Information about documentations

  #230 opened a year ago by zixuan417
  1

• Question about the implementation of PPO actor loss function

  #229 opened a year ago by ZiyiLiubird
  2

• Are visual agents supported?

  #214 opened a year ago by davidoort
  2

• Can not reproduce SMAC results.

  #222 opened a year ago by ZiyiLiubird
  5

• TypeError

  #221 opened a year ago by ZiyiLiubird
  2

• frames comparison within max epoch if

  #212 opened a year ago by ankurhanda
  9

• Wandb does not seem to record time or step correctly

  #208 opened 2 years ago by DanielTakeshi
  3

• Ways of integrating already existing knowledges into SAC training?

  #211 opened 2 years ago by famora2
  1