Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics
arXiv:2005.04269
Abstract
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 method---Truncated Quantile Critics, TQC,---blends 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.
Under review by the International Conference on Machine Learning
References in corpus (5)
- Rainbow: Combining Improvements in Deep Reinforcement Learning
- A Distributional Perspective on Reinforcement Learning
- Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
- Distributional Reinforcement Learning with Quantile Regression
- Estimating the Maximum Expected Value: An Analysis of (Nested) Cross Validation and the Maximum Sample Average