Deep Reinforcement Learning for Playing 2.5D Fighting Games

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.

arXiv commentICIP 2018

References in corpus (6)

• Prioritized Experience Replay
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• StarCraft II: A New Challenge for Reinforcement Learning
• Deep reinforcement learning from human preferences
• Massively Parallel Methods for Deep Reinforcement Learning
• Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic