EqR: Equivariant Representations for Data-Efficient Reinforcement Learning

Arnab Kumar Mondal, Vineet Jain, Kaleem Siddiqi, Siamak Ravanbakhsh

Abstract: We study a variety of notions of equivariance as an inductive bias in Reinforcement Learning (RL). In particular, we propose new mechanisms for learning representations that are equivariant to both...