werner-duvaud/muzero-general

Issues

• Is there a place we can see and share results for each game?

  #196 opened 3 years ago by onegigbyte
  0

• Breakout: ModuleNotFoundError shows gym[atari] instead of python-opencv

  #223 opened 2 years ago by velicanerdem
  1

• Chess and other non-trivial games

  #231 opened 10 months ago by StepHaze
  2

• Sampled MuZero implementation

  #191 opened 3 years ago by matthiaskiller
  1

• Only One Player: Can we use MuZero?

  #210 opened 2 years ago by 1121091694
  2

• Without Selfplay, why 1 games on a running??

  #217 opened 2 years ago by dlrlfkr11
  2

• What does the `replay_buffer.pkl` do?

  #228 opened a year ago by dmtrung14
  1

• cross play between models

  #229 opened a year ago by dmtrung14
  0

• The model does not converge for breakout

  #211 opened 2 years ago by yungangwu
  11

• How can I use a pre-trained model?

  #227 opened a year ago by worldsoft
  1

• Update gym package to gymnasium

  #219 opened 2 years ago by Mlokos
  1

• MuZero choose the same action

  #226 opened a year ago by sdumi03
  0

• Muzero crashes when choosing spiel/backgammon

  #225 opened a year ago by artshar
  0

• question about action encoded

  #222 opened 2 years ago by Nightbringers
  0

• The difference between offical pseudo code and this repository about "num_unroll_steps"

  #221 opened 2 years ago by ZF4444
  0

• Dirichlet noise added outside of training

  #220 opened 2 years ago by TommyX12
  0

• Mean_value plot in Total_reward - Interpretation

  #215 opened 2 years ago by SunilaAkbar
  0

• Question about the dimension of value and reward network

  #214 opened 2 years ago by jiachengc
  0

• Can't train using GPU? The torch version for this environment is '1.10.0cpu', that is, CPU one.

  #213 opened 2 years ago by SunilaAkbar
  2

• Question about the perspective transformation of two players when calculating Q?

  #212 opened 2 years ago by puyuan1996
  0

• TypeError: can't pickle function objects

  #208 opened 2 years ago by OopsYouDiedE
  0

• MuZero Unplugged

  #185 opened 3 years ago by tbskrpmnns
  7

• Question: Does muzero-general support 2 player games with simultaneous action selection?

  #207 opened 2 years ago by moscoso
  3

• ray.exceptions.RayActorError: The actor died unexpectedly before finishing this task.

  #182 opened 3 years ago by hairinwind
  1

• Render model

  #197 opened 3 years ago by theeduardomora
  1

• Remove Batch Norm?

  #203 opened 2 years ago by verbose-void
  0

• OpenGL rendering on a remote server over X11

  #202 opened 2 years ago by jrjbertram
  0

• RuntimeError: module must have its parameters and buffers on device cuda:0 (device_ids[0]) but found one of them on device: cpu

  #174 opened 3 years ago by lukaszkn
  3

• [Question] Is the environment required to have no hidden information?

  #201 opened 2 years ago by ZhengWenZhang
  0

• raw install has ray problem

  #198 opened 2 years ago by EngrStudent
  1

• sampling in continuous/complex action spaces with 'density prior' is not working

  #200 opened 2 years ago by ManorZ
  0

• Batch MCTS

  #199 opened 2 years ago by szrlee
  0

• Policy target after MCTS should be in form of probabilities

  #193 opened 3 years ago by 2M-kotb
  1

• custom observation transformation

  #195 opened 3 years ago by SimpleMathmatics
  0

• Can muzero learn to play two different games at the same time

  #189 opened 3 years ago by lwaif
  1

• Dimensionality issue in continuous action space

  #165 opened 3 years ago by alik604
  1

• Target Value Offset

  #170 opened 3 years ago by dans-acc
  1

• Scaling of historical stacked observations

  #178 opened 3 years ago by tuero
  1

• training result cannot be loaded on another machine

  #180 opened 3 years ago by hairinwind
  1

• Entropy loss in continuous actions

  #175 opened 3 years ago by 2M-kotb
  4

• Strange observations and actions in continuous implementation.

  #186 opened 3 years ago by dylanamiller
  1

• Struggling to get Ray working

  #171 opened 3 years ago by SheldonCurtiss
  0

• Why is root.visit_count initialized to 0 and root_predicted_value not included in root node value?

  #184 opened 3 years ago by dniku
  0

• procgen

  #183 opened 3 years ago by hlsfin
  0

• Why my game does not remember the steps trained

  #181 opened 3 years ago by hairinwind
  3

• Total Training Reward rises then drops again

  #176 opened 3 years ago by annahambi
  2

• Is there a more optimized way to complete training? Every game has to be learned for so long, people learn to master it early

  #173 opened 3 years ago by lwaif
  1

• Scrabble implementation - How to include Player's rack observation

  #167 opened 3 years ago by nicolasnijssen
  2

• Would it possible to write go game and chess game program?

  #166 opened 3 years ago by leqingli2000
  1

• could it run without ray?

  #164 opened 3 years ago by hilberthu
  2