Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning

Abstract

Sample efficiency is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks can significantly improve sample efficiency. Recent research indicates that successor feature (SF) RL algorithms enable knowledge generalization between tasks with different rewards but identical transition dynamics. It has recently been hypothesized that combining model-based (MB) methods with SF algorithms can alleviate the limitation of fixed transition dynamics. Furthermore, uncertainty-aware exploration is widely recognized as another appealing approach for improving sample efficiency. Putting together two ideas of hybrid model-based successor feature (MB-SF) and uncertainty leads to an approach to the problem of sample efficient uncertainty-aware knowledge transfer across tasks with different transition dynamics or/and reward functions. In this paper, the uncertainty of the value of each action is approximated by a Kalman filter (KF)-based multiple-model adaptive estimation. This KF-based framework treats the parameters of a model as random variables. To the best of our knowledge, this is the first attempt at formulating a hybrid MB-SF algorithm capable of generalizing knowledge across large or continuous state space tasks with various transition dynamics while requiring less computation at decision time than MB methods. The number of samples required to learn the tasks was compared to recent SF and MB baselines. The results show that our algorithm generalizes its knowledge across different transition dynamics, learns downstream tasks with significantly fewer samples than starting from scratch, and outperforms existing approaches.

40 pages

References in corpus (15)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• An Introduction to Variational Autoencoders
• Gaussian Processes for Data-Efficient Learning in Robotics and Control
• First return, then explore
• Provably Efficient Reinforcement Learning with Linear Function Approximation
• Successor Features for Transfer in Reinforcement Learning
• Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
• Transfer learning for galaxy morphology from one survey to another
• Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints
• A neurally plausible model learns successor representations in partially observable environments
• Toward the biological model of the hippocampus as the successor representation agent
• Risk-Aware Transfer in Reinforcement Learning using Successor Features
• AKF-SR: Adaptive Kalman Filtering-based Successor Representation
• Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
• Learning One Representation to Optimize All Rewards