1,484 Hits in 7.9 sec

Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking [article]

Yue Wang, Yao Wan, Chenwei Zhang, Lixin Cui, Lu Bai, Philip S. Yu
2019 arXiv   pre-print
In particular, we propose a multi-agent deep reinforcement learning model with a structure which mimics the human-psychological counterfactual thinking process to improve the competitive abilities for  ...  This paper investigates the counterfactual thinking for agents to find optimal decision-making strategies in multi-agent reinforcement learning environments.  ...  This also verifies that the counterfactual thinking mechanism is useful in training agent to solve the multi-agent deep reinforcement learning problems.  ... 
arXiv:1908.04573v2 fatcat:ouxrpzum7fc7dpnw4mxjm2sfpu

Counterfactual-Based Action Evaluation Algorithm in Multi-Agent Reinforcement Learning

Yuyu Yuan, Pengqian Zhao, Ting Guo, Hongpu Jiang
2022 Applied Sciences  
Therefore, we propose a novel counterfactual reasoning-based multi-agent reinforcement learning algorithm to evaluate the continuous contribution of agent actions on the latent state.  ...  Multi-agent reinforcement learning (MARL) algorithms have made great achievements in various scenarios, but there are still many problems in solving sequential social dilemmas (SSDs).  ...  Section 3 elaborates on the counterfactual-based multi-agent reinforcement learning algorithm with simulation reasoning and action evaluation network.  ... 
doi:10.3390/app12073439 fatcat:qd25rdbukbbhfkaubtyalciumi

Extending World Models for Multi-Agent Reinforcement Learning in MALMÖ

Valliappa Chockalingam, Tegg Tae Kyong Sung, Feryal Behbahani, Rishab Gargeya, Amlesh Sivanantham, Aleksandra Malysheva
2018 Artificial Intelligence and Interactive Digital Entertainment Conference  
Recent work in (deep) reinforcement learning has increasingly looked to develop better agents for multi-agent/multitask scenarios as many successes have already been seen in the usual single-task single-agent  ...  These choices include the following: using model-based agents which allows for planning/simulation and reduces computation costs when learning controllers, applying distributional reinforcement learning  ...  Secondly, as the tasks in the MARLÖ competition involve multi-agent multi-task scenarios, we need to think about how to train the agents.  ... 
dblp:conf/aiide/ChockalingamSBG18 fatcat:g63hnabnwzejtjw4lxms5dwhc4

Generation of Traffic Flows in Multi-Agent Traffic Simulation with Agent Behavior Model based on Deep Reinforcement Learning [article]

Junjie Zhong, Hiromitsu Hattori
2021 arXiv   pre-print
by using deep reinforcement learning based on a combination of regenerated visual images revealing some notable features, and numerical vectors containing some important data such as instantaneous speed  ...  In multi-agent based traffic simulation, agents are always supposed to move following existing instructions, and mechanically and unnaturally imitate human behavior.  ...  The relationship among agents in multi-agent system is considered to be cooperative, competitive or mixed cooperative competitive and so on.  ... 
arXiv:2101.03230v2 fatcat:g372dntmqnhsfgpo2yxhr6fqnq

Pommerman: A Multi-Agent Playground [article]

Cinjon Resnick, Wes Eldridge, David Ha, Denny Britz, Jakob Foerster, Julian Togelius, Kyunghyun Cho, Joan Bruna
2022 arXiv   pre-print
We present Pommerman, a multi-agent environment based on the classic console game Bomberman.  ...  believe that success in Pommerman will require a diverse set of tools and methods, including planning, opponent/teammate modeling, game theory, and communication, and consequently can serve well as a multi-agent  ...  This is especially true for multi-agent Deep RL. We think that the reasons for that could be among the five above.  ... 
arXiv:1809.07124v2 fatcat:i6icm5u45rgwvjziksmktyr4ty

A Survey and Critique of Multiagent Deep Reinforcement Learning [article]

Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor
2019 arXiv   pre-print
reinforcement learning settings.  ...  The primary goal of this article is to provide a clear overview of current multiagent deep reinforcement learning (MDRL) literature.  ...  Frans Oliehoek, Sam Devlin, Marc Lanctot, Nolan Bard, Roberta Raileanu, Angeliki Lazaridou, and Yuhang Song for clarifications in their areas of expertise, to Baoxiang Wang for his suggestions on recent deep  ... 
arXiv:1810.05587v2 fatcat:h4ei5zx2xfa7xocktlefjrvef4

Deep Reinforcement Learning, a textbook [article]

Aske Plaat
2022 arXiv   pre-print
Developments go quickly, and we also cover advanced topics: deep multi-agent reinforcement learning, deep hierarchical reinforcement learning, and deep meta learning.  ...  The aim of this book is to provide a comprehensive overview of the field of deep reinforcement learning.  ...  Competitive, Cooperative, and Mixed Strategies Multi-agent reinforcement learning problems fall into three groups: problems with competitive behavior, with cooperative behavior, and with mixed behavior  ... 
arXiv:2201.02135v2 fatcat:3icsopexerfzxa3eblpu5oal64

AI in Human-computer Gaming: Techniques, Challenges and Opportunities [article]

Qiyue Yin, Jun Yang, Kaiqi Huang, Meijing Zhao, Wancheng Ni, Bin Liang, Yan Huang, Shu Wu, Liang Wang
2022 arXiv   pre-print
With breakthrough of the AlphaGo, human-computer gaming AI has ushered in a big explosion, attracting more and more researchers all around the world.  ...  distributed deep reinforcement learning.  ...  Training for Commander Similar with AlphaStar, Commander adopts a very similar training framework for StarCraft agent learning, i.e, supervised learning followed by multi-agent reinforcement learning.  ... 
arXiv:2111.07631v2 fatcat:ee476rnax5bydbca673vgh2utm

ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learning [article]

Hangyu Mao, Zhibo Gong, Yan Ni, Zhen Xiao
2017 arXiv   pre-print
The ACCNet naturally combines the powerful actor-critic reinforcement learning technology with deep learning technology.  ...  Typically, most previous multi-agent "learning-to-communicate" studies try to predefine the communication protocols or use technologies such as tabular reinforcement learning and evolutionary algorithm  ...  It uses a counterfactual baseline and a centralised critic to address multi-agent credit assignment problem.  ... 
arXiv:1706.03235v3 fatcat:ejrksp7d5rchlja76n7f3icyfi

OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning

Alexander Vezhnevets, Yuhuai Wu, Maria Eckstein, Rémi Leblond, Joel Z. Leibo
2020 International Conference on Machine Learning  
It turns out that most current deep reinforcement learning methods fail to efficiently explore the strategy space, thus learning policies that generalise poorly to unseen opponents.  ...  We propose two new games with concealed information and complex, non-transitive reward structure (think rock/paper/scissors).  ...  The first contribution of this paper are two grid world multi-agent games with simple implementation, yet complex multi-agent dynamics with non-transitive reward (think rock/paper/scissors) and concealed  ... 
dblp:conf/icml/VezhnevetsWELL20 fatcat:m5o3fkh5ona7hhuz756lz53ixe

Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game [article]

Pablo Barros, Ana Tanevska, Alessandra Sciutti
2020 arXiv   pre-print
Endowing artificial agents with this ability is not a simple task, particularly in competitive scenarios.  ...  In this paper, we present a broad study on how popular reinforcement learning algorithms can be adapted and implemented to learn and to play a real-world implementation of a competitive multiplayer card  ...  INTRODUCTION With the current interest in reinforcement learning caused by the development of deep reinforcement learning techniques [1] , novel methods and mechanisms have been developed in recent years  ... 
arXiv:2004.04000v1 fatcat:nyxwwo425rfhhinaxud4s2djeq

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning [article]

Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, Ji Liu
2021 arXiv   pre-print
Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.  ...  Unfortunately, modern reinforcement learning algorithms mainly focus on simple and small action spaces, and not surprisingly, are shown not to make satisfactory progress in DouDizhu.  ...  NIPS Deep Reinforcement Learning Symposium, 2017. Zhou, H., Zhang, H., Zhou, Y., Wang, X., and Li, W. Bot- zone: an online multi-agent competitive platform for ai education.  ... 
arXiv:2106.06135v1 fatcat:juy7mpjt7zcntjrgw77uh5flk4

Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms [article]

Kaiqing Zhang, Zhuoran Yang, Tamer Başar
2021 arXiv   pre-print
., the games of Go and Poker, robotics, and autonomous driving, involve the participation of more than one single agent, which naturally fall into the realm of multi-agent RL (MARL), a domain with a relatively  ...  Recent years have witnessed significant advances in reinforcement learning (RL), which has registered great success in solving various sequential decision-making problems in machine learning.  ...  In particular, DeepStack applies deep learning to learn good representations of the game and proposes deep counterfactual value networks to integrate deep learning and CFR.  ... 
arXiv:1911.10635v2 fatcat:ihlhtjlhnrdizbkcfzsnz5urfq

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.  ...  We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details.  ...  Lanctot et al. (2017) observe that independent RL, in which each agent learns by interacting with the environment, oblivious to other agents, can overfit the learned policies to other agents' policies  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning [article]

Md Masudur Rahman, Yexiang Xue
2022 arXiv   pre-print
Deep Reinforcement Learning (RL) agents often overfit the training environment, leading to poor generalization performance.  ...  The bootstrapped trajectories are then used for policy learning. Thinker has wide applicability among many RL settings.  ...  Introduction Deep reinforcement learning has achieved tremendous success.  ... 
arXiv:2207.07749v1 fatcat:fsu7pgaywvdctiwglswvlyq6ha
« Previous Showing results 1 — 15 out of 1,484 results