Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

Michal Nauman; Michał Bortkiewicz; Piotr Miłoś; Tomasz Trzcinski; Mateusz Ostaszewski; Marek Cygan

2024 ICML ICML 2024

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Michal Nauman, Michał Bortkiewicz, Piotr Miłoś, Tomasz Trzcinski, Mateusz Ostaszewski, Marek Cygan

Topics

Reinforcement Learning > Methods > Deep RL Reinforcement Learning > Methods > Policy Learning Reinforcement Learning > Applications > Robotics

Keywords

regularization plasticity loss soft actor-critic overfitting overestimation gradient update steps

Download PDF