Abstract. This paper presents a new approach to representation discovery in reinforcement learning (RL) using basis adaptation.

Jun 30, 2013 · This paper presents a new approach to representation discovery in reinforcement learning (RL) using basis adaptation. We introduce a general ...

Mar 8, 2023 · Basis Adaptation for Sparse Nonlinear Reinforcement Learning · Authors · Proceedings: · Issue: · Track: · Downloads: Download PDF. Proceedings ...

This paper presents a new approach to representation discovery in reinforcement learning (RL) using basis adaptation. We introduce a general framework for ...

This paper presents a new approach to representation discovery in reinforcement learning (RL) using basis adaptation. We introduce a general framework for ...

Bibliographic details on Basis Adaptation for Sparse Nonlinear Reinforcement Learning.

Abstract. A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to ...

Abstract. When using reinforcement learning (RL) algorithms it is common, given a large state space, to introduce some form of approximation architecture ...

Inspired by Knoll & de Freitas (2012) , we propose an expressive sparse non-linear feature representation which we call locality sensitive sparse encoding. Our ...

Abstract We propose a model-based online reinforcement learning approach for continuous domains with deterministic transitions using a spatially adaptive ...