Multi-method learning and assimilation

Takamuku, Shinya; Arkin, Ronald C.

doi:10.1016/j.robot.2007.04.001

Cited by 11 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ease the assimilation of multiple targets, current HRL approaches often use the same or similar methods within one application. However, there is no single method that can benefit all targets (Wolpert and Macready, 1997;Takamuku and Arkin, 2007;Tan et al, 2011;Abbaszadeh Shahri and Maghsoudi Moud, 2021), which is also applicable to HRL. The choice of methods will depend on the type of tasks and rewards, the attributes of the state and action spaces, etc.…”

Section: Hybrid Learningmentioning

confidence: 99%

Online robot guidance and navigation in non-stationary environment with hybrid Hierarchical Reinforcement Learning

Zhou

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Section: Hybrid Learningmentioning

confidence: 99%

Online robot guidance and navigation in non-stationary environment with hybrid Hierarchical Reinforcement Learning

Zhou

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…Assimilation and accommodation represent forms of the maintenance and modification of these cognitive schemata [21]. Takamuku and Arkin [22] applied assimilation on domestic robots for social learning, enabling the robots to perform well under various situations. This study proposes both bevel-angle and positive-angle accommodation strategies for modifying the agent's cognitive structure.…”

Section: Assimilation and Accommodationmentioning

confidence: 99%

Multiagent Cooperative Learning Strategies for Pursuit-Evasion Games

Kuo

Liu

et al. 2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This study examines the pursuit-evasion problem for coordinating multiple robotic pursuers to locate and track a nonadversarial mobile evader in a dynamic environment. Two kinds of pursuit strategies are proposed, one for agents that cooperate with each other and the other for agents that operate independently. This work further employs the probabilistic theory to analyze the uncertain state information about the pursuers and the evaders and uses case-based reasoning to equip agents with memories and learning abilities. According to the concepts of assimilation and accommodation, both positive-angle and bevel-angle strategies are developed to assist agents in adapting to their environment effectively. The case study analysis uses the Recursive Porous Agent Simulation Toolkit (REPAST) to implement a multiagent system and demonstrates superior performance of the proposed approaches to the pursuit-evasion game.

show abstract

“…Recent work has taken place under the name of multi method learning. 24 In this work, a new strategy for behavior acquisition for domestic robots is proposed. Behaviors are acquired using multiple differing learning methods that are subsequently incorporated into a common behavior selection system, enabling them to be performed in appropriate situations.…”

Section: Multi Agent Machine Learningmentioning

confidence: 99%

Sharing in teams of heterogeneous, collaborative learning agents

Gifford

Agah

2009

Int. J. Intell. Syst.

View full text Add to dashboard Cite

This paper is focused on the effects of sharing knowledge and collaboration of multiple heterogeneous, intelligent agents (hardware or software) which work together to learn a task. As each agent employs a different machine learning technique, the system consists of multiple knowledge sources and their respective heterogeneous knowledge representations. Collaboration between agents involves sharing knowledge to both speed up team learning, as well as refine the team's overall performance and group behavior. Experiments have been performed that vary the team composition in terms of machine learning algorithms, learning strategies employed by the agents, and sharing frequency for a predator-prey cooperative pursuit task. For lifelong learning, heterogeneous learning teams were more successful than homogeneous learning counterparts. Interestingly, sharing increased the learning rate, but sharing with higher frequency showed diminishing results. Lastly, knowledge conflicts are reduced over time the more sharing takes place. These results support further investigation of the merits of heterogeneous learning. C 2008 Wiley Periodicals, Inc.

show abstract

Multi-method learning and assimilation

Cited by 11 publications

References 19 publications

Online robot guidance and navigation in non-stationary environment with hybrid Hierarchical Reinforcement Learning

Online robot guidance and navigation in non-stationary environment with hybrid Hierarchical Reinforcement Learning

Multiagent Cooperative Learning Strategies for Pursuit-Evasion Games

Sharing in teams of heterogeneous, collaborative learning agents

Contact Info

Product

Resources

About