Deep Reinforcement Learning for Playing 2.5D Fighting Games (2018-05-05T00:00:00.000000Z)

TL;DR

An OpenAI-gym-like gaming environment is created with the game of Little Fighter 2 (LF2), and a novel A3C+ network is presented for learning RL agents, which includes a Recurrent Info network, which utilizes game-related info features with recurrent layers to observe combo skills for fighting.

Abstract

Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreover, actions in such games typically involve particular sequential action orders, which also makes the network design very difficult. Based on the network of Asynchronous Advantage Actor-Critic (A3C), we create an OpenAI-gym-like gaming environment with the game of Little Fighter 2 (LF2), and present a novel A3C+ network for learning RL agents. The introduced model includes a Recurrent Info network, which utilizes game-related info features with recurrent layers to observe combo skills for fighting. In the experiments, we consider LF2 in different settings, which successfully demonstrates the use of our proposed model for learning 2.5D fighting games.

Authors

Y. Wang

5 papers

Yu-Jhe Li

1 papers

Hsin-Yu Chang

1 papers

Deep Reinforcement Learning for Playing 2.5D Fighting Games

TL;DR

Abstract

Authors

References22 items

StarCraft II: A New Challenge for Reinforcement Learning

Proximal Policy Optimization Algorithms

Deep Reinforcement Learning from Human Preferences

Multi-agent Reinforcement Learning in Sequential Social Dilemmas

Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning

Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic

Playing FPS Games with Deep Reinforcement Learning

OpenAI Gym

ViZDoom: A Doom-based AI research platform for visual reinforcement learning

A Deep Hierarchical Approach to Lifelong Learning in Minecraft

Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation

Asynchronous Methods for Deep Reinforcement Learning

Mastering the game of Go with deep neural networks and tree search

Prioritized Experience Replay

Deep Recurrent Q-Learning for Partially Observable MDPs

Massively Parallel Methods for Deep Reinforcement Learning

MuJoCo: A physics engine for model-based control

The Arcade Learning Environment: An Evaluation Platform for General Agents

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories

“https://github.com

http://www.projectf.hk

http://www.littlefighter.com

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names