The proximal policy optimization (PPO) algorithm stands as one of the most prosperous methods in the field of reinforcement learning (RL). Despite its success, the theoretical understanding of PPO remains deficient. Specifically, it is unclear whether PPO or its optimistic variants can effectively solve linear Markov decision processes (MDPs), which are arguably the simplest models in RL with function approximation.

The process for calculating these metrics is described in Appendix C. Moreover, to ensure the comparability between prediction performance metrics and driving performance metrics in the radar plot, we normalize all metrics to the scale of [0, 1]. In the subsequent section, we provide an overview of the DESPOT planner. These two values can only be inferred from history. The safety is represented by the normalized collision rate.

Training offline RL models using visual inputs poses two significant challenges, i.e.,