Analyzing Action Masking in the MiniHack Reinforcement Learning Environment

Autor:	Cannon, Ian
Jazyk:	angličtina
Rok vydání:	2022
Předmět:	Computer Engineering Computer Science reinforcement learning action masking rl environment minihack nethack ppo neural networks policy action augmentation action space meta facebook research exploration game games game design multimodal observations
Druh dokumentu:	Text
Popis:	Reinforcement Learning (RL) is an area of machine learning that enables an agent to learn in an interactive environment by trial and error using feedback from its own actions and experiences. NetHack presents a challenging problem for RL. It has a very large action space and multimodal observation space while requiring an agent to be capable of planning hundreds of thousands of timesteps to achieve a difficult goal. MiniHack is presented by Facebook AI Research to provide a testbed to develop incremental solutions toward the monumental goal of completing an ascension in NetHack. It presents a powerful framework for designing RL environments in procedurally generated worlds. Toward success in MiniHack, this thesis describes a method for masking actions to reduce the action space of agents. This thesis shows that masking actions can provide an effective means to artificially reduce the action space of any agent. Reducing the action space has been shown to increase the sample efficiency of agents in environments with large action spaces to few relevant actions.
Databáze:	Networked Digital Library of Theses & Dissertations
Externí odkaz:	http://rave.ohiolink.edu/etdc/view?acc_num=dayton1671013536765918 Zobrazit plný text záznamu