Playing Doom with Anticipator-A3C Based Agents Using Deep Reinforcement Learning and the ViZDoom Game-AI Research Platform

These days game AI is one of the focused and active research areas in artificial intelligence because computer games are the best test-beds for testing theoretical ideas in AI before practically applying them in real life world. Similarly, ViZDoom is a game artificial intelligence research platform based on Doom used for visual deep reinforcement learning in 3D game environments such as first-person shooters (FPS). While training, the speed of the learning agent greatly depends on the number of frames the agent is permitted to skip. In this paper, how the frame skipping rate influences the agent’s learning and final performance is proposed, particularly using deep Q-learning, experience replay memory, and the ViZDoom Game AI research platform. The agent is trained and tested on Doom’s basic scenario(s) where the results are compared and found to be 10% better compared to the existing state-of-the-art research work on Doom-based agents. The experiments show that the profitable and optimal frame skipping rate falls in the range of 3 to 11 that provides the best balance between the learning speed and the final performance of the agent which exhibits human-like behavior and outperforms an average human player and inbuilt game agents.

Download Full-text

A Study on Application of Curriculum Learning in Deep Reinforcement Learning : Action Acquisition in Shooting Game AI as Example

10.1109/iwcia52852.2021.9626020 ◽

2021 ◽

Author(s):

Ikumi Kodaka ◽

Fumiaki Saitoh

Keyword(s):

Reinforcement Learning ◽

Game Ai

Download Full-text

Combining Case-Based Reasoning and Reinforcement Learning for Unit Navigation in Real-Time Strategy Game AI

Case-Based Reasoning Research and Development - Lecture Notes in Computer Science ◽

10.1007/978-3-319-11209-1_36 ◽

2014 ◽

pp. 511-525 ◽

Cited By ~ 10

Author(s):

Stefan Wender ◽

Ian Watson

Keyword(s):

Reinforcement Learning ◽

Real Time ◽

Case Based Reasoning ◽

Game Ai ◽

Strategy Game ◽

Real Time Strategy Game ◽

Case Based

Download Full-text

Applying Reinforcement Learning for Game AI in a Tank-Battle Game

2009 Fourth International Conference on Innovative Computing, Information and Control (ICICIC) ◽

10.1109/icicic.2009.114 ◽

2009 ◽

Cited By ~ 1

Author(s):

Yung-Ping Fang ◽

I-Hsien Ting

Keyword(s):

Reinforcement Learning ◽

Game Ai

Download Full-text

Reinforcement learning with adaptive Kanerva coding for Xpilot game AI

2011 IEEE Congress of Evolutionary Computation (CEC) ◽

10.1109/cec.2011.5949796 ◽

2011 ◽

Cited By ~ 9

Author(s):

Martin Allen ◽

Phil Fritzsche

Keyword(s):

Reinforcement Learning ◽

Game Ai

Download Full-text

Playing Card-Based RTS Games with Deep Reinforcement Learning

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/631 ◽

2019 ◽

Author(s):

Tianyu Liu ◽

Zijie Zheng ◽

Hongchang Li ◽

Kaigui Bian ◽

Lingyang Song

Keyword(s):

Reinforcement Learning ◽

Decision Tree ◽

State Space ◽

Imperfect Information ◽

Rule Based ◽

Playing Card ◽

Board Games ◽

Deep Model ◽

Game Ai ◽

Rts Game

Game AI is of great importance as games are simulations of reality. Recent research on game AI has shown much progress in various kinds of games, such as console games, board games and MOBA games. However, the exploration in RTS games remains a challenge for their huge state space, imperfect information, sparse rewards and various strategies. Besides, the typical card-based RTS games have complex card features and are still lacking solutions. We present a deep model SEAT (selection-attention) to play card-based RTS games. The SEAT model includes two parts, a selection part for card choice and an attention part for card usage, and it learns from scratch via deep reinforcement learning. Comprehensive experiments are performed on Clash Royale, a popular mobile card-based RTS game. Empirical results show that the SEAT model agent makes it to reach a high winning rate against rule-based agents and decision-tree-based agent.

Download Full-text