rail-berkeley/softlearning

Issues

• Error on installing with docker

  #167 opened 4 years ago by Mahdi-HF
  1

• The issue of softlearning implementation

  #203 opened a year ago by Ziyu0118
  1

• why target entropy is -dim(A)?

  #200 opened 2 years ago by mittu1008
  0

• using deterministic policy in enviroment like lunarlander?

  #193 opened 3 years ago by MohammadAsadolahi
  0

• Question on initialization of alpha and entropy

  #149 opened 4 years ago by dbsxdbsx
  7

• target_entropy discrete_space

  #162 opened 4 years ago by Maggern3
  2

• Implementation of automatic entropy temperature tuning(alpha loss)

  #163 opened 4 years ago by Maggern3
  6

• `dm_control` `cheetah` `run` training stops suddenly

  #151 opened 4 years ago by letusfly85
  3

• Differences between softlearning implementation and formula 18 in paper of alpha loss

  #177 opened 4 years ago by Maggern3
  0

• Incompatible with ray 1.2.0

  #169 opened 4 years ago by xanderdunn
  1

• Incompatible with tensorflow 2.4.0

  #170 opened 4 years ago by xanderdunn
  1

• MultiGoal Env not working, please give instruction.

  #165 opened 4 years ago by qlinsey
  6

• SQL algorithm is not working

  #164 opened 4 years ago by ivan-ji-walmart
  1

• No module named 'example.instruments'

  #161 opened 4 years ago by ndormann
  2

• No module named 'examples.instrument'

  #117 opened 5 years ago by ling-pan
  1

• No rendering/headless mode available?

  #158 opened 4 years ago by khatch31
  0

• How can I generate eval/test output video of dm_control tasks?

  #153 opened 4 years ago by letusfly85
  0

• error when running example

  #152 opened 4 years ago by eleyng
  0

• Not use GPU failed call to cuInit: CUDA_ERROR_NO_DEVICE

  #150 opened 4 years ago by letusfly85
  4

• Results folder should be configurable through cli

  #128 opened 4 years ago by hartikainen
  0

• Non-MuJoCo examples?

  #115 opened 5 years ago by david-masters
  0

• Question on the soft q learning implementation

  #143 opened 5 years ago by YuxuanSong
  1

• Policy weights and output becomes NaN after some iterations

  #136 opened 5 years ago by charlesjsun
  5

• SAC gradients weighted inconsistently

  #141 opened 5 years ago by hartikainen
  0

• base_policy to_yaml fails

  #135 opened 5 years ago by kapsl
  2

• Using keras functional API in model

  #138 opened 5 years ago by kapsl
  3

• Question about multiple CPU usage.

  #137 opened 5 years ago by charlesjsun
  3

• Training step limit breaks logging

  #139 opened 5 years ago by hartikainen
  0

• --restore not working anymore?

  #134 opened 5 years ago by kapsl
  1

• Possibility to show structure of the model

  #133 opened 5 years ago by kapsl
  1

• A fatal error occurred

  #129 opened 5 years ago by Max-918
  2

• Several issues

  #130 opened 5 years ago by kapsl
  3

• examples/development/simulate_policy.py is broken

  #131 opened 5 years ago by hartikainen
  0

• Training speed of new code is much slower than before

  #124 opened 5 years ago by kapsl
  2

• Are there plans to integrate DisCor

  #125 opened 5 years ago by kapsl
  2

• tune.sample_from parallelized

  #126 opened 5 years ago by kapsl
  1

• Simulating policy now broken

  #113 opened 5 years ago by nflu
  0

• Multiple conflicts in requirements.txt

  #123 opened 5 years ago by johannespitz
  6

• Nan error in Humanoid

  #120 opened 5 years ago by varun-intel
  2

• Conda installation problem Ubuntu 18.04

  #111 opened 5 years ago by Jendker
  3

• 'FeedforwardGaussianPolicy' object has no attribute '_Serializable__initialize'

  #107 opened 5 years ago by ZhanPython
  1

• trials did not complete error

  #98 opened 5 years ago by surbhi1944
  5

• Can not save checkpoint

  #104 opened 5 years ago by mohsinlakhani
  3

• Is there an example of using the Google Cloud Engine version of the launcher?

  #106 opened 5 years ago by kapsl
  0

• Installing on Docker

  #105 opened 5 years ago by kapsl
  1

• ModulesNotFound - systems.path related issue

  #103 opened 5 years ago by weijiafeng
  1

• Stuck on KMP_AFFINITY thread allocation issue

  #102 opened 5 years ago by weijiafeng
  2

• Benchmark Result

  #101 opened 5 years ago by lujiayou123
  1

• Mujoco license - invalid key in docker container

  #99 opened 6 years ago by mbed92
  1

• LSTM Support

  #97 opened 6 years ago by pethor
  1