A Composite Architecture for a Realistic Blocks World Domain
نویسنده
چکیده
I present a domain-specific architecture targeted for a real-world version of the Blocks World domain called “Real” Blocks World. The architecture design attempts to include the best features of several popular Agent Architecures, while mitigating their weaknesses. Agent functionality is considered in light of environment scenarios, single-agent, and multiagent systems.
منابع مشابه
A Novel Temporal-Frequency Domain Error Concealment Method for Motion Jpeg
Motion-JPEG is a common video format for compression of motion images with highquality using JPEG standard for each frame of the video. During transmission through a noisychannel some blocks of data are lost or corrupted, and the quality of decompression frames decreased.In this paper, for reconstruction of these blocks, several temporal-domain, spatial-domain, andfrequency-domain error conceal...
متن کاملInstance-Based Online Learning of Deterministic Relational Action Models
We present an instance-based, online method for learning action models in unanticipated, relational domains. Our algorithm memorizes preand post-states of transitions an agent encounters while experiencing the environment, and makes predictions by using analogy to map the recorded transitions to novel situations. Our algorithm is implemented in the Soar cognitive architecture, integrating its t...
متن کاملWhat Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances
This paper describes an architecture for an agent to learn and reason about affordances. In this architecture, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete domain knowledge that includes a representation of affordances as relations defined jointly over objects and actions. Reinforcement learning and decision-tree induction based on this relational r...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملThe "Limit" Domain
Proof planning is an application of AI-planning in mathematical domains. As opposed to planning for domains such as blocks world or transportation, the domain knowledge for mathematical domains is difllcult to extract. Hence proof planning requires clever knowledge engineering and representation of the domain knowledge. We think that on the one hand, the resulting domain definitions that includ...
متن کامل