Enabling Off-Policy Imitation Learning with Deep Actor Critic Stabilization

ArXi:2511.07288v2 Announce Type: replace Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the difficulty of reward engineering. Imitation Learning (IL) from expert nstrations bypasses this reliance on rewards. However, state-of-the-art IL methods, exemplified by Generative Adversarial Imitation Learning (GAIL)Ho et. al, suffer from severe sample inefficiency. This is a direct consequence of their foundational on-policy algorithms, such as TRPO Schulman et.al. In this work, we