Proximal Policy Optimization with Adaptive Exploration

Autor:	Lixandru, Andrei
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute new insights into reinforcement learning algorithm design. The proposed adaptive exploration framework dynamically adjusts the exploration magnitude during training based on the recent performance of the agent. Our proposed method outperforms standard PPO algorithms in learning efficiency, particularly when significant exploratory behavior is needed at the beginning of the learning process.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.04664 Zobrazit plný text záznamu View this record from Arxiv