Adaptive Reward Penalty in Safe Reinforcement Learning

Boris Meinardus, Tuan Anh Le, Rong Guo

Keywords: Safe RL, RCPO, PPO

Abstract: In this blog, we dive into the ICLR 2019 paper "Reward Constrained Policy Optimization" (RCPO) by Tessler et al. and highlight the importance of adaptive reward shaping in safe reinforcement learning. We reproduce the paper's experimental results by implementing RCPO into Proximal Policy Optimization (PPO). This blog aims to provide researchers and practitioners with (1) a better understanding of safe reinforcement learning in terms of constrained optimization and (2) how penalized reward functions can be effectively used to train a robust policy.

Blogpost Url: https://iclr-blogposts.github.io/staging/blog/2023/Adaptive-Reward-Penalty-in-Safe-Reinforcement-Learning/

ICLR Papers: https://arxiv.org/abs/1805.11074

ID Of The Authors Of The ICLR Paper: ~Boris_Meinardus1

Conflict Of Interest: No