Skill transfer through goal-driven representation mapping

Könik, Tolga; O'Rorke, Paul; Shapiro, David; Choi, Dongkyu; Nejati, Negin; Langley, Pat

doi:10.1016/j.cogsys.2008.09.008

Cited by 11 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Banerjee and Stone extracted high-level features from the value functions learned on one GGP game to accelerate learning in another [15] . Outside of the GGP context, Könik et al learn "tasks" suitable for transfer within the current environment (if the same problem comes up again later on) or to other environments with similar tasks by biasing value functions when similarities are found [16]. We believe AGDL could support this latter type of learning, giving a way to bridge high-level design concepts across games and to learn tactics and high-level actions within a given game.…”

Section: B G(v)gpmentioning

confidence: 99%

Automated game design learning

Osborn

Summerville

Mateas

2017

2017 IEEE Conference on Computational Intelligence and Games (CIG)

View full text Add to dashboard Cite

While general game playing is an active field of research, the learning of game design has tended to be either a secondary goal of such research or it has been solely the domain of humans. We propose a field of research, Automated Game Design Learning (AGDL), with the direct purpose of learning game designs directly through interaction with games in the mode that most people experience games: via play. We detail existing work that touches the edges of this field, describe current successful projects in AGDL and the theoretical foundations that enable them, point to promising applications enabled by AGDL, and discuss next steps for this exciting area of study. The key moves of AGDL are to use game programs as the ultimate source of truth about their own design, and to make these design properties available to other systems and avenues of inquiry.

show abstract

Section: B G(v)gpmentioning

confidence: 99%

Automated game design learning

Osborn

Summerville

Mateas

2017

2017 IEEE Conference on Computational Intelligence and Games (CIG)

View full text Add to dashboard Cite

show abstract

“…Both this work and that of Könic et al (Könik et al, 2009) map between concepts in order to apply knowledge from one situation to another. There are some differences between this work and (Könik et al, 2009). This technique is proposed to derive links between previously unrelated concepts.…”

Section: Related Workmentioning

confidence: 99%

Explanation-based learning with analogy for impasse resolution

Timperley

Mokhtar

Bellaby

et al. 2016

Expert Systems with Applications

View full text Add to dashboard Cite

This paper proposes an algorithm for the inclusion of analogy into Explanation-Based Learning (EBL). Analogy can be used when an impasse is reached to extend the deductive closure of EBL's domain theory. This enables the generation of control laws, via EBL, for hardware which is not catered for in the domain theory. This advantage addresses a problem which represents a dearth in the current literature. Integrated Modular Avionics (IMA) literature has thus far been concerned with the architectural considerations. This paper seeks to address the impact of hardware changes on the controllers within an IMA architecture. An algorithm is proposed and applied to control an aviation platform with an incomplete domain theory. Control rules are generated when no deductive explanations are possible, which still reflect the intent of the domain theory.

show abstract

“…Reinforcement learning, learning from demonstration and active imitation offer promising perspectives in that direction, e.g., [7,60,107] and approaches mentioned in Section 3.1.2. Learning descriptive models of actions and skills is an active area of research, e.g., [112,61,66,110,111], in which many challenges remain to address in the integrative actor's requirements.…”

Section: Model Acquisition and Verificationmentioning

confidence: 99%

The actorʼs view of automated planning and acting: A position paper

Ghallab

Nau

Traverso³

2014

Artificial Intelligence

View full text Add to dashboard Cite

Planning is motivated by acting. Most of the existing work on automated planning underestimates the reasoning and deliberation needed for acting; it is instead biased towards path-finding methods in a compactly specified state-transition system. Researchers in this AI field have developed many planners, but very few actors. We believe this is one of the main causes of the relatively low deployment of automated planning applications. In this paper, we advocate a change in focus to actors as the primary topic of investigation. Actors are not mere plan executors: they may use planning and other deliberation tools, before and during acting. This change in focus entails two interconnected principles: a hierarchical structure to integrate the actor's deliberation functions, and continual online planning and reasoning throughout the acting process. In the paper, we discuss open problems and research directions toward that objective in knowledge representations, model acquisition and verification, synthesis and refinement, monitoring, goal reasoning, and integration.

show abstract

Skill transfer through goal-driven representation mapping

Cited by 11 publications

References 15 publications

Automated game design learning

Automated game design learning

Explanation-based learning with analogy for impasse resolution

The actorʼs view of automated planning and acting: A position paper

Contact Info

Product

Resources

About