Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics
Arsenii Kuznetsov,u00a0Pavel Shvechikov,u00a0Alexander Grishin,u00a0Dmitry Vetrov
The overestimation bias is one of the major impediments to accurate off-policy learning. This paper investigates a novel way to alleviate the overestimation bias in a continuous control setting. Our methodu2014Truncated Quantile Critics, TQC,u2014blends three ideas: distributional representation of a critic, truncation of critics prediction, and ensembling of multiple critics. Distributional representation and truncation allow for arbitrary granular overestimation control, while ensembling provides additional score improvements. TQC outperforms the current state of the art on all environments from the continuous control benchmark suite, demonstrating 25% improvement on the most challenging Humanoid environment.
