rr-learning/CausalWorld

Issues

• to use OpenGL3 with X11

  #110 opened 2 years ago by CHbloom
  1

• Trained baseline models perform poorly

  #100 opened 3 years ago by zrjnz
  1

• Stage using unexpected client ID

  #106 opened 2 years ago by phlippe
  2

• Observation mode "pixel" raises AttributeError

  #105 opened 2 years ago by phlippe
  2

• gym.GoalEnv decapricated from gym.version >= 0.21

  #103 opened 3 years ago by michaelfeil
  1

• How to record higher quality videos?

  #99 opened 4 years ago by ekarais
  1

• correctness and speed of TriFinger._safety_torque_check

  #101 opened 3 years ago by michaelfeil
  5

• Add intervention for time left for the task

  #13 opened 4 years ago by ossamaAhmed
  0

• investigating reaching task after refactoring

  #35 opened 4 years ago by ftraeuble
  0

• save wrappers and restore them in a better way

  #63 opened 4 years ago by ossamaAhmed
  0

• save_state test is failing

  #59 opened 4 years ago by ossamaAhmed
  0

• trifinger_pro

  #97 opened 4 years ago by s-bl
  1

• Torque-mode wrong achieved_goal

  #80 opened 4 years ago by martius-lab
  0

• set_full_state of stage broken

  #83 opened 4 years ago by s-bl
  3

• towers: reward engineering

  #36 opened 4 years ago by ftraeuble
  0

• reward wrong in reaching task

  #79 opened 4 years ago by martius-lab
  1

• computation of PD gains and save-state

  #81 opened 4 years ago by martius-lab
  0

• is_not_fixed wrong call

  #82 opened 4 years ago by ossamaAhmed
  0

• Add intervention for the height of robot

  #9 opened 4 years ago by ossamaAhmed
  1

• propagate size to intervention spaces height of blocks!

  #67 opened 4 years ago by ossamaAhmed
  0

• add orientation to intervention_spaces

  #69 opened 4 years ago by ossamaAhmed
  0

• do intervention without checking bounds?

  #65 opened 4 years ago by ossamaAhmed
  0

• td3 hyperparams for all tasks

  #38 opened 4 years ago by ftraeuble
  0

• her integration for baseline tasks

  #39 opened 4 years ago by ftraeuble
  0

• rename observation modes

  #61 opened 4 years ago by ftraeuble
  0

• pick_and_place goal sampler

  #64 opened 4 years ago by ossamaAhmed
  0

• verify camera images with new edu platform

  #66 opened 4 years ago by ossamaAhmed
  0

• Add callback function during training to track fractional success and animate intermediate step policies

  #18 opened 4 years ago by ftraeuble
  0

• Rename Intervention Spaces

  #29 opened 4 years ago by ossamaAhmed
  0

• Fix Intervention Actors

  #30 opened 4 years ago by ossamaAhmed
  1

• Set up CI

  #15 opened 4 years ago by ossamaAhmed
  0

• pick and place: reward engineering

  #37 opened 4 years ago by ftraeuble
  0

• pushing reward engineering

  #34 opened 4 years ago by ftraeuble
  0

• ppo rlpyt integration picking

  #33 opened 4 years ago by ftraeuble
  0

• SAC rlpyt integration picking

  #32 opened 4 years ago by ftraeuble
  0

• Latching starting state doesnt seem to be bug free with stacked blocks generator

  #27 opened 4 years ago by ossamaAhmed
  0

• update evaluation protocols for benchmark task distributions

  #17 opened 4 years ago by ftraeuble
  0

• Memory Leak in Action Mode as End Effector Positions Caused by pybullet

  #7 opened 4 years ago by ossamaAhmed
  1

• training reaching with ppo2 indicates memory leak

  #3 opened 4 years ago by ftraeuble
  1

• MPC tutorial is not working anymore

  #8 opened 4 years ago by ossamaAhmed
  0