Multi-Agent Deep Reinforcement Learning with Human Strategies

2018-06-12 · Thanh Nguyen, Ngoc Duy Nguyen, Saeid Nahavandi

Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In this paper, we introduce an approach that integrates human strategies to increase the exploration capacity of multiple deep reinforcement learning agents. We also report the development of our own multi-agent environment called Multiple Tank Defence to simulate the proposed approach. The results show the significant performance improvement of multiple agents that have learned cooperatively with human strategies. This implies that there is a critical need for human intellect teamed with machines to solve complex problems. In addition, the success of this simulation indicates that our multi-agent environment can be used as a testbed platform to develop and validate other multi-agent control algorithms.

📄 PDF Abstract BibTeX arXiv:1806.04562

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion

2025-08-14 · Qi Liu, Xiaopeng Zhang, Mingshan Tan, Shuaikang Ma 외 arxiv

This paper proposes a novel method to enhance locomotion for a single humanoid robot through cooperative-heterogeneous multi-agent deep reinforcement learning (MARL). While most existing methods typically employ single-a…

Multi-agent Reinforcement Learning

Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI

2022-11-04 · Emily Halina, Matthew Guzdial

In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strat…

Deep Reinforcement Learning Diversity reinforcement-learning Reinforcement Learning (RL)

Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning

2023-06-01 · Andrew Liu, Alla Borisyuk

Navigation is a complex skill with a long history of research in animals and humans. In this work, we simulate the Morris Water Maze in 2D to train deep reinforcement learning agents. We perform automatic classification …

Deep Reinforcement Learning reinforcement-learning

Evaluating Persuasion Strategies and Deep Reinforcement Learning methods for Negotiation Dialogue agents

2017-04-01 · EACL 2017 4 · Simon Keizer, Markus Guhe, Heriberto Cuay{\'a}huitl, Ioannis Efstathiou 외

In this paper we present a comparative evaluation of various negotiation strategies within an online version of the game {``}Settlers of Catan{''}. The comparison is based on human subjects playing games against artifici…

Deep Reinforcement Learning Persuasion Strategies reinforcement-learning Reinforcement Learning+1

Learning to Communicate in Multi-Agent Reinforcement Learning : A Review

2019-11-13 · Mohamed Salah Zaïem, Etienne Bennequin

We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)