nicklashansen/tdmpc

Issues

• [Q]: Manipulator tasks and visualization

  #19 opened 10 months ago by Ozzey
  2

• [Q]: Termination Prevention Logic

  #14 opened a year ago by ArashAhmadian
  2

• Intuition behind using LayerNorm in Q function?

  #5 opened 3 years ago by mch5048
  2

• Package for Plots

  #18 opened a year ago by MianchuWang
  1

• I encountered some problems during training

  #17 opened a year ago by like2000522
  2

• Discrepancy between code and implementation regarding the planned action

  #16 opened 2 years ago by odelalleau
  2

• How to visualize the evaluation process？

  #15 opened 2 years ago by zsn2021
  1

• Intuition behind using zero initialization in critic and reward model last layer

  #13 opened 2 years ago by hdadong
  1

• Multimodal data as input to the model

  #10 opened 2 years ago by SergioArnaud
  1

• Why don't have Meta-World task in the task.txt?

  #9 opened 2 years ago by 945716994
  1

• Implementation in Openai Atari gym

  #12 opened 2 years ago by zrbak
  1

• the setting of random seed

  #8 opened 2 years ago by Arya87
  1

• Why I can't save the video?

  #7 opened 2 years ago by Bailey-24
  1

• Question about base.device

  #6 opened 3 years ago by pickxiguapi
  1

• Typo in the arxived paper and some question on the notation.

  #4 opened 3 years ago by mch5048
  1

• A Question about mpc and td-mpc

  #3 opened 3 years ago by wenzhoulyu
  4

• Other envs

  #2 opened 3 years ago by wenzhoulyu
  2

• how to adapt to discrete action space

  #1 opened 3 years ago by Howuhh
  1