Investigating Reinforcement Learning Agents for Continuous State Space Environments

• Abstract
• Abstract (translated by Google)
• URL
• PDF

Abstract

Given an environment with continuous state spaces and discrete actions, we investigate using a Double Deep Q-learning Reinforcement Agent to find optimal policies using the LunarLander-v2 OpenAI gym environment.

Abstract (translated by Google)

URL

http://arxiv.org/abs/1708.02378

PDF

http://arxiv.org/pdf/1708.02378