florensacc/rllab-curriculum

Issues

• Question about the reward

  #8 opened 6 years ago by tldoan
  3

• Question about the lsgan loss(hyperparameters a, b and c)

  #23 opened 4 years ago by zhangyx96
  0

• Visualize the training

  #22 opened 4 years ago by amir-ramezani-ai
  0

• Doesn't work after training?

  #21 opened 4 years ago by davidsonic
  1

• libmujoco131.so: cannot open shared object file: No such file or directory

  #18 opened 4 years ago by Bahar-nkr
  1

• the definition of 'done' in step function from arm3d_disc_env

  #19 opened 5 years ago by mushroom1116
  3

• the definition of 'done' in step function from arm3d_disc_env

  #20 opened 5 years ago by mushroom1116
  1

• which file was used for the evaluation points of Key insertion environment?

  #17 opened 6 years ago by tldoan
  1

• Precision about the training parameters? (mainly TRPO )

  #16 opened 6 years ago by tldoan
  0

• Wrong environments in the default setup

  #14 opened 6 years ago by srinivr
  0

• x, y limits are interchanged

  #13 opened 6 years ago by srinivr
  0

• Evaluation point for PointMass environment

  #12 opened 6 years ago by tldoan
  1

• How long approximatively it takes to run on AntMaze?

  #9 opened 6 years ago by tldoan
  1

• Having "nan" value when using wrapped env "GoalStartExplorationEnv"

  #11 opened 6 years ago by tldoan
  1

• Problem rendering PointMazeEnv and coordinates reading

  #10 opened 6 years ago by tldoan
  0

• using OpenAI gym env

  #1 opened 6 years ago by arpit15
  1

• running arm3d env experiments

  #2 opened 6 years ago by arpit15
  1

• Problem running MazeAntEnv

  #4 opened 6 years ago by ahq1993
  3

• Could goal GAN solve the sparse reward atari game Montezuma Revenge?

  #5 opened 6 years ago by nina124
  1

• how to render?

  #6 opened 6 years ago by LanxinL
  1

• Question about generate_starts function for reverse curriculum

  #7 opened 6 years ago by tldoan
  1

• Convergence criteria for arm3d?

  #3 opened 6 years ago by therealchuckliu
  4