A factorization perspective for learning representations in reinforcement learning
نویسنده
چکیده
Reinforcement learning is a general formalism for sequential decision-making, with recent algorithm development focusing on function approximation to handle large state spaces and high-dimensional, high-velocity (sensor) data. The success of function approximators, however, hinges on the quality of the data representation. In this work, we explore representation learning within batch reinforcement learning, with a focus on making the assumptions on the representation explicit and making the learning problem amenable to principled optimization techniques. We specify a reinforcement learning objective for value function learning that facilitates the addition of a regularized matrix factorization objective to specify the desired class of representations. The resulting joint optimization over the representation and value function parameters enables us to take advantages of recent advances in unsupervised learning and presents a general yet simple formalism for learning representations in reinforcement learning.
منابع مشابه
Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملIntegrating representation learning and temporal difference learning: A matrix factorization approach
Reinforcement learning is a general formalism for sequential decision-making, with recent algorithm development focusing on function approximation to handle large state spaces and high-dimensional, high-velocity (sensor) data. The success of function approximators, however, hinges on the quality of the data representation. In this work, we explore representation learning within least-squares te...
متن کاملImage 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 کاملReinforcement Learning in Robotics: Applications and Real-World Challenges
In robotics, the ultimate goal of reinforcement learning is to endow robots with the ability to learn, improve, adapt and reproduce tasks with dynamically changing constraints based on exploration and autonomous learning. We give a summary of the state-of-the-art of reinforcement learning in the context of robotics, in terms of both algorithms and policy representations. Numerous challenges fac...
متن کاملStudy of the Factors Affecting on the Quality of Virtual Learning and Education from the Perspective of Dental Students of Zahedan University of Medical Sciences
Abstract Background & Aim: Nowadays the use of digital technology in dental education hasdramatically increased. The growth and development of educational models shows that it is important to change the approach of education from traditional methods to electronic methods and virtual education. We conducted the present study in aims of investigating the effective factors on the quality of vir...
متن کامل