Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
Despite the recent success of reinforcement learning in various domains, these approaches remain, for the most part, deterringly sensitive to hyper-parameters and are often riddled with essential engineering feats allowing their success. We consider the case of off-policy generative adversarial imitation learning, and perform an in-depth review, qualitative and quantitative, of the method. Crucially, we show that forcing the learned reward function to be local Lipschitz-continuous is a sine qua non condition for the method to perform well. We then study the effects of this necessary condition and provide several theoretical results involving the local Lipschitzness of the state-value function. Finally, we propose a novel reward-modulation technique inspired from a new interpretation of gradient-penalty regularization in reinforcement learning. Besides being extremely easy to implement and bringing little to no overhead, we show that our method provides improvements in several continuous control environments of the MuJoCo suite.
READ FULL TEXT