UBCMOCCA/SymmetricRL

Future Work

Closed this issue · 0 comments

  • new environments
    • non-locomotion
    • more symmetries: Ant, Sudoku
    • quadruped (raisim)
  • symmetric gait
    • as a reward: r_t = | s_t - M(s_{t-T/2}) |
    • as a differentiable loss?
  • revisiting PHASE for non-imitation tasks
    • better designed env
    • adaptible/foot strike based?
      • based on last foot strike side?
  • unique net for each config