AKF-SR: Adaptive Kalman Filtering-based Successor Representation

TL;DR

This paper introduces AKF-SR, a novel adaptive Kalman filtering framework for Successor Representation that estimates uncertainty, improves learning efficiency, and enhances decision-making in reinforcement learning tasks.

Contribution

It develops a Kalman filter-based SR model with adaptive noise tuning and an active learning policy to better manage uncertainty and improve reward acquisition.

Findings

AKF-SR effectively estimates uncertainty in SR.

Adaptive noise tuning improves learning stability.

Active learning enhances reward performance.

Abstract

Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared to that of model-based algorithms. However, it is not known how such representation might help animals to manage uncertainty in their decision-making. Existing methods for SR learning do not capture uncertainty about the estimated SR. In order to address this issue, the paper presents a Kalman filter-based SR framework, referred to as Adaptive Kalman Filtering-based Successor Representation (AKF-SR). First, Kalman temporal difference approach, which is a combination of the Kalman filter and the temporal difference method, is used within the AKF-SR framework to cast the SR learning procedure into a filtering problem to benefit from the uncertainty estimation of the SR, and also decreases in memory requirement and sensitivity to model's parameters in comparison to deep neural network-based algorithms. An adaptive Kalman filtering approach is then applied within the proposed AKF-SR framework in order to tune the measurement noise covariance and measurement mapping function of Kalman filter as the most important parameters affecting the filter's performance. Moreover, an active learning method that exploits the estimated uncertainty of the SR to form the behaviour policy leading to more visits to less certain values is proposed to improve the overall performance of an agent in terms of received rewards while interacting with its environment.