2003
DOI: 10.1016/s0921-8890(03)00040-x
|View full text |Cite
|
Sign up to set email alerts
|

An approach to the pursuit problem on a heterogeneous multiagent system using reinforcement learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
42
0
3

Year Published

2005
2005
2022
2022

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 70 publications
(45 citation statements)
references
References 3 publications
0
42
0
3
Order By: Relevance
“…In a popular variant, several "predator" robots have to capture a "prey" robot by converging on it [83], [96].…”
Section: B Robotic Teamsmentioning
confidence: 99%
See 1 more Smart Citation
“…In a popular variant, several "predator" robots have to capture a "prey" robot by converging on it [83], [96].…”
Section: B Robotic Teamsmentioning
confidence: 99%
“…In these cases, approximate solutions must be sought, e.g., by extending to multiple agents the work on approximate singleagent RL [111]- [122]. A fair number of approximate MARL algorithms have been proposed: for discrete, large state-action spaces, e.g., [123], for continuous states and discrete actions, e.g., [96], [98], and [124], and finally for continuous states and actions, e.g., [95], and [125]. Unfortunately, most of these algorithms only work in a narrow set of problems and are heuristic in nature.…”
Section: A Practical Marlmentioning
confidence: 99%
“…Another investigation of the pursuit domain is that of Ishiwaka et al [71], which considers heterogeneous agents in a continuous state-action world with partial, noisy observations. In this work, the authors investigate how the predators can learn online using Q-learning.…”
Section: Pursuit Domainmentioning
confidence: 99%
“…Thus, there is no need to observe the other agent's actual rewards received from the environment, and to know the parameters that the other agent uses for Q-learning. Finally, Ishiwaka et al [19] presented a method for two kinds of prediction needed for each hunter agent acting in pursuit domain. One of these predictions is the location of the other hunter agents and prey agent, and the other is the movement direction of the prey agent at the next time step.…”
Section: B Multiagent Learning Fuzzy Modular Approach With Internal mentioning
confidence: 99%