Representation Transfer via Elaboration
نویسندگان
چکیده
Introduction A key component of any reinforcement learning (RL) algorithm is the underlying representation used by the agent for learning (e.g. the parameterization of its function approximator). Transfer learning tasks typically look at speeding up a target task after learning in a source task. This paper considers a different, but related, question: is it possible, and desirable, for agents to transfer from a source representation to a target representation? Elaboration, presented below, is a representation transfer (RT) algorithm that may allow an agent to learn faster than learning with a single representation. One motivation for such flexibility is learning speed: changing representations partway through learning may allow agents to achieve better performance in less time. SOAR (Laird, Newell, & Rosenbloom 1987) can use multiple descriptions of planning problems and search problems, generated by a human user, for just this reason. Other work (Sherstov & Stone 2005) suggests that gradually reducing the generalization of a function approximator may improve the speed of learning. In this paper we suggest that it is advantageous to modify the internal representation while learning in some RL tasks, relative to using a fixed representation, so that higher performance is achieved more quickly.
منابع مشابه
Image Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
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 Effect of Semantic Transfer on Iranian EFL Learners’ Lexical Representation and Processing
متن کامل
Deblocking Joint Photographic Experts Group Compressed Images via Self-learning Sparse Representation
JPEG is one of the most widely used image compression method, but it causes annoying blocking artifacts at low bit-rates. Sparse representation is an efficient technique which can solve many inverse problems in image processing applications such as denoising and deblocking. In this paper, a post-processing method is proposed for reducing JPEG blocking effects via sparse representation. In this ...
متن کاملNovagen: A Combination of Eyesweb and an Elaboration-Network Representation for the Generation of Melodies under Gestural Control
A system which generates melodies influenced by the movements of a dancer is described. Underlying the melody-generation is a representation based on the theory of the early 20thcentury German musicologist, Heinrich Schenker: a melody is derived from a simple background by layers of elaboration. Overall, the theory has similarities to a generative grammar. Generation of melodies is achieved by ...
متن کامل