Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development

Asada, Minoru; Uchibe, Eiji; Hosoda, Koh

doi:10.1016/s0004-3702(99)00026-0

Cited by 112 publications

(48 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, few have entered into a critical dialogue concerning the relationship between having a body and the emergence of intelligence. Here, we review the significance of embodiment [4].…”

Section: Physical Embodiment and Interactionsmentioning

confidence: 99%

“…Furthermore, other agents can be coaches or teachers who can communicate with robots by various means. From the viewpoint of facilitating a robot's development, learning from easy missions [1], a learning schedule [4], or a gradual increase in domain complexity [33] are typical approaches.…”

Section: Environmental Design Issuesmentioning

confidence: 99%

“…While at first it may seem that we are looking at the problem the wrong way around -adapting the task to the robot rather than the robot to the task -this is in fact what parents do naturally in finding stimulating, age-appropriate ways of interacting with their children. Asada et al [4] defined the complexity of the environment in terms of the relationship between self-induced motor commands and changes in sensory input.…”

Section: Environmental Complexity Controlmentioning

confidence: 99%

“…We introduced a learning schedule [4] to address the first problem which only one agent is allowed to learn. The other agents have fixed policies until the learner's skill reaches a pre-specified level.…”

Section: Learning Schedules In Multi-agent Learningmentioning

confidence: 99%

See 3 more Smart Citations

Cognitive developmental robotics as a new paradigm for the design of humanoid robots

Asada

MacDorman

Ishiguro

et al. 2001

Robotics and Autonomous Systems

Self Cite

352

163

View full text Add to dashboard Cite

This paper proposes cognitive developmental robotics (CDR) as a new principle for the design of humanoid robots. This principle may provide ways of understanding human beings that go beyond the current level of explanation found in the natural and social sciences. Furthermore, a methodological emphasis on humanoid robots in the design of artificial creatures holds promise because they have many degrees of freedom and sense modalities and, thus, must face the challenges of scalability that are often side-stepped in simpler domains. We examine the potential of this new principle as well as issues that are likely to be important to CDR in the future.

show abstract

Section: Physical Embodiment and Interactionsmentioning

confidence: 99%

Section: Environmental Design Issuesmentioning

confidence: 99%

Section: Environmental Complexity Controlmentioning

confidence: 99%

Section: Learning Schedules In Multi-agent Learningmentioning

confidence: 99%

See 2 more Smart Citations

Cognitive developmental robotics as a new paradigm for the design of humanoid robots

Asada

MacDorman

Ishiguro

et al. 2001

Robotics and Autonomous Systems

Self Cite

352

163

View full text Add to dashboard Cite

show abstract

“…Asada et al [4] proposed a method that sets a global learning schedule in which only one agent is specified as a learner with the rest of the agents having fixed policies. Accordingly, the method cannot handle the alternation of the opponent's policies.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous Learning to Acquire Competitive Behaviors in Multi-agent System Based on Modular Learning System

Takahashi

Edazawa

Noma

et al. 2006

RoboCup 2005: Robot Soccer World Cup IX

Self Cite

View full text Add to dashboard Cite

Abstract-Existing reinforcement learning approaches have been suffering from the policy alternation of others in multiagent dynamic environments. A typical example is the case of RoboCup competitions because other agent behaviors may cause sudden changes in state transition probabilities in which constancy is needed for the learning to converge. The keys for simultaneous learning to acquire competitive behaviors in such an environment are• a modular learning system for adaptation to the policy alternation of others; and • an introduction of macro actions for simultaneous learning to reduce the search space. This paper presents a method of modular learning in a multiagent environment in which the learning agents can simultaneously learn their behaviors and adapt themselves to the situations as a consequence of the others' behaviors.

show abstract

PEXIS: Probabilistic experience representation based adaptive interaction system for personal robots

Inamura

Inaba

Inoue

2004

Systems & Computers in Japan

View full text Add to dashboard Cite

SUMMARYIn this paper the authors focus on the interaction between users and personal robots that can move in a real environment. When the creation of robots that can perform in an ordinary home or office is considered, it is difficult to imagine beforehand what kind of environment will be used, and so the approach in which developers embed environmental knowledge and strategies for autonomous movement fails. Thus, the authors propose an approach in which knowledge of the environment and the knowledge needed to move are acquired after development by allowing the robot and the user who is using the robot to engage in dialogue, and representing experience statistically. The authors introduce PEXIS, an interaction system developed using this approach, and then describe the characteristics and utility of their system via examples such as learning to avoid objects in an office environment and adapting to the vocabulary expressions of a particular user.

show abstract

Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development

Cited by 112 publications

References 19 publications

Cognitive developmental robotics as a new paradigm for the design of humanoid robots

Cognitive developmental robotics as a new paradigm for the design of humanoid robots

Simultaneous Learning to Acquire Competitive Behaviors in Multi-agent System Based on Modular Learning System

PEXIS: Probabilistic experience representation based adaptive interaction system for personal robots

Contact Info

Product

Resources

About