add reacher env and all mujoco envs now support COT, SPP, SELF-REFLEXION, EXE methods under L1&L3 setting. 8f842da CharlesZhang commited on Jan 8
add 5 more envs: halfcheetah, hopper, walker2d, invertedPendulum, invertedDoublePendulum. 2ec5014 CharlesZhang commited on Jan 7
