59,835 Hits in 10.9 sec

AI in Games: Techniques, Challenges and Opportunities [article]

Qiyue Yin, Jun Yang, Wancheng Ni, Bin Liang, Kaiqi Huang
2021 arXiv   pre-print
In this paper, we survey recent successful game AIs, covering board game AIs, card game AIs, first-person shooting game AIs and real time strategy game AIs.  ...  Finally, we hope this brief review can provide an introduction for beginners, inspire insights for researchers in the filed of AI in games.  ...  Firstly, in the selection stage, a node is selected based on the sum of action value Q and a bonus u(p).  ... 
arXiv:2111.07631v1 fatcat:g4sbl6v73rg4jdijj4qfi3eusq

Combining imagination and heuristics to learn strategies that generalize [article]

Erik J Peterson, Necati Alp Müyesser, Timothy Verstynen, Kyle Dunovan
2020 arXiv   pre-print
Deep reinforcement learning can match or exceed human performance in stable contexts, but with minor changes to the environment artificial networks, unlike humans, often cannot adapt.  ...  We test performance of this network using Wythoff's game, a gridworld environment with a known optimal strategy.  ...  strategies in more complex environments.  ... 
arXiv:1809.03406v2 fatcat:g7mbudu43bgejnsv24ewvm7c2y

Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks [article]

Kai Olav Ellefsen, Jim Torresen
2019 arXiv   pre-print
A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules.  ...  Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models.  ...  Background Model-based reinforcement learning The problems we target in this paper are reinforcement learning (RL) problems, meaning an agent is tasked with learning how to solve some problem without  ... 
arXiv:1904.02435v2 fatcat:mhkyehmllzecfmhxbmmqmvjbve

Asynchronous Advantage Actor-Critic Agent for Starcraft II [article]

Basel Alghanem, Keerthana P G
2018 arXiv   pre-print
In this project we explain the complexities of this environment and discuss the results from our experiments on the environment.  ...  We have compared various architectures and have proved that transfer learning can be an effective paradigm in reinforcement learning research for complex scenarios requiring skill transfer.  ...  SC2LE (StarCraft II Learning Environment) [6] is a new challenge for exploring reinforcement learning algorithms and architectures, based on the StarCraft II video game.  ... 
arXiv:1807.08217v1 fatcat:fpiprhvfdbfk5g4vtkoysy6xlu

Multiagent Reinforcement Learning With Sparse Interactions by Negotiation and Knowledge Transfer

Luowei Zhou, Pei Yang, Chunlin Chen, Yang Gao
2017 IEEE Transactions on Cybernetics  
Reinforcement learning has significant applications for multi-agent systems, especially in unknown dynamic environments.  ...  However, most multi-agent reinforcement learning (MARL) algorithms suffer from such problems as exponential computation complexity in the joint state-action space, which makes it difficult to scale up  ...  In this paper, we focus on solving learning problems in complex systems.  ... 
doi:10.1109/tcyb.2016.2543238 pmid:27046917 fatcat:oocm7ykxufg5tko7546gefqkr4

A Survey of Deep Reinforcement Learning in Video Games [article]

Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao
2019 arXiv   pre-print
Deep reinforcement learning (DRL) has made great achievements since proposed.  ...  We also take a review of the achievements of DRL in various video games, including classical Arcade games, first-person perspective games and multi-agent real-time strategy games, from 2D to 3D, and from  ...  Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL) use deep reinforcement learning to learn endto-end communication protocols in complex environments.  ... 
arXiv:1912.10944v2 fatcat:fsuzp2sjrfcgfkyclrsyzflax4

StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning [article]

Kun Shao, Yuanheng Zhu, Dongbin Zhao
2018 arXiv   pre-print
We define an efficient state representation, which breaks down the complexity caused by the large state space in the game environment.  ...  With reinforcement learning and curriculum transfer learning, our units are able to learn appropriate strategies in StarCraft micromanagement scenarios.  ...  In this paper, we focus on a real-time strategy (RTS) game to explore the learning of multi-agent control.  ... 
arXiv:1804.00810v1 fatcat:mlskaiafdjd4rdfdtvwq7wozaa

Object-Oriented Representation and Hierarchical Reinforcement Learning in Infinite Mario

M. Joshi, R. Khobragade, S. Sarda, U. Deshpande, S. Mohan
2012 2012 IEEE 24th International Conference on Tools with Artificial Intelligence  
In this work, we analyze and improve upon reinforcement learning techniques used to build agents that can learn to play Infinite Mario, an action game.  ...  We also extend the idea of hierarchical RL by designing a hierarchy in action selection using domain specific knowledge.  ...  Furthermore, the agent cannot transfer its learning in between different levels of the game. An RL framework, on the other hand, is capable of this transfer. V.  ... 
doi:10.1109/ictai.2012.152 dblp:conf/ictai/JoshiKSDM12 fatcat:dkj4fj6jonb57oxcsvtkwb67qy

Mutual Reinforcement Learning [article]

Sayanti Roy, Emily Kieson, Charles Abramson, Christopher Crick
2019 arXiv   pre-print
In this paper we demonstrate the application and effectiveness of a new approach called mutual reinforcement learning (MRL), where both humans and autonomous agents act as reinforcement learners in a skill  ...  An autonomous agent initially acts as an instructor who can teach a novice human participant complex skills using the MRL strategy.  ...  ACKNOWLEDGMENTS This work was supported by NSF award #1527828 (NRI: Collaborative Goal and Policy Learning from Human Operators of Construction Co-Robots).  ... 
arXiv:1907.06725v3 fatcat:t6am5r6jzfc3pj5p664rrz7asy

Optimising market share and profit margin: SMDP-based tariff pricing under the smart grid paradigm

Rodrigue T. Kuate, Maria Chli, Hai H. Wang
2014 IEEE PES Innovative Smart Grid Technologies, Europe  
This paper puts forward a reinforcement-learning-powered tool aiding an electricity retailer to define the tariff prices it offers, in a bid to optimise its retail strategy.  ...  To evaluate our trading strategy, we developed a retailer agent (termed AstonTAC) that uses the proposed SMDP framework to act in an open multi-agent simulation environment, the Power Trading Agent Competition  ...  The advantage of the SMDP and reinforcement learning is that it enables the retailer agent to adapt to the strategy changes of game opponents using the environment states.  ... 
doi:10.1109/isgteurope.2014.7028942 fatcat:leksheha5jcdpj7t2zdabxqrai

Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey [article]

Aske Plaat, Walter Kosters, Mike Preuss
2020 arXiv   pre-print
Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics.  ...  Model-based reinforcement learning creates an explicit model of the environment dynamics to reduce the need for environment samples.  ...  ACKNOWLEDGMENTS We thank the members of the Leiden Reinforcement Learning Group, and especially Thomas Moerland and Mike Huisman, for many discussions and insights.  ... 
arXiv:2008.05598v2 fatcat:5xmwmemv5bfinkw57avf5ghhxq

Deep Reinforcement Learning, a textbook [article]

Aske Plaat
2022 arXiv   pre-print
The way in which deep reinforcement learning explores complex environments reminds us of how children learn, by playfully trying out things, getting feedback, and trying again.  ...  Deep reinforcement learning has gathered much attention recently. Impressive results were achieved in activities as diverse as autonomous driving, game playing, molecular recombination, and robotics.  ...  The rst AlphaGo program used supervised learning based on grandmaster games, followed by reinforcement learning on self-play games.  ... 
arXiv:2201.02135v2 fatcat:3icsopexerfzxa3eblpu5oal64

Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL

Manu Sharma, Michael P. Holmes, Juan Carlos Santamaría, Arya Irani, Charles Lee Isbell Jr., Ashwin Ram
2007 International Joint Conference on Artificial Intelligence  
It uses a novel combination of Case-Based Reasoning (CBR) and Reinforcement Learning (RL) to achieve transfer while playing against the Game AI across a variety of scenarios in MadRTS TM , a commercial  ...  Real Time Strategy game.  ...  Acknowledgements We would like to thank Santi Ontañón for valuable feedback and the anonymous IJCAI reviewers for a variety of suggestions on this paper.  ... 
dblp:conf/ijcai/SharmaHSIIR07 fatcat:bbjii5zvfbg7fay5ftj52gyr64

Transfer Learning in Attack Avoidance Games

Edwin Torres, Fernando Lozano
2020 Journal of Computer Science  
In this study, we present a new strategy to facilitate knowledge transfer when an agent is learning to solve a sequence of increasing difficulty tasks.  ...  Transfer knowledge is a human characteristic that has been replicated in machine learning algorithms to improve learning performance measures.  ...  Each one of these strategies finds knowledge in a different location and based on that implements a method to transfer it.  ... 
doi:10.3844/jcssp.2020.1465.1476 fatcat:iqea3cqpvbdubgk7mmrxybnlcu

Towards autonomous behavior learning of non-player characters in games

Shu Feng, Ah-Hwee Tan
2016 Expert systems with applications  
in one framework.  ...  In view of their complementary strengths, this paper proposes a computational model unifying the two learning paradigms based on a class of self-organizing neural networks called Fusion Architecture for  ...  In the game environment, each NPC is essentially an autonomous agent, which is expected to function and adapt by themselves in a complex and dynamic environment.  ... 
doi:10.1016/j.eswa.2016.02.043 fatcat:vfsatkxgdfcv7is3gb4kgatydm
« Previous Showing results 1 — 15 out of 59,835 results