
By exploiting symmetries in the dynamical model, independent of the reward function, this work presents a method to learn more accurate dynamical models that can improve sample efficiency in model-based reinforcement learning.


coremsg

leveraging-symmetry-in-dynamics-for-efficient-model-based-reinforcement-learning-with-asymmetric-rewards


Leveraging Symmetry in Dynamics for Efficient Model-Based Reinforcement Learning with Asymmetric Rewards
