DeepAI AI Chat
Log In Sign Up

An Optimal Online Method of Selecting Source Policies for Reinforcement Learning

09/24/2017
by   Siyuan Li, et al.
0

Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance yet challenging. There has been little theoretical analysis of this problem. In this paper, we develop an optimal online method to select source policies for reinforcement learning. This method formulates online source policy selection as a multi-armed bandit problem and augments Q-learning with policy reuse. We provide theoretical guarantees of the optimal selection process and convergence to the optimal policy. In addition, we conduct experiments on a grid-based robot navigation domain to demonstrate its efficiency and robustness by comparing to the state-of-the-art transfer learning method.

READ FULL TEXT

page 4

page 6

06/11/2018

Context-Aware Policy Reuse

Transfer learning can greatly speed up reinforcement learning for a new ...
01/22/2018

Cross-Domain Transfer in Reinforcement Learning using Target Apprentice

In this paper, we present a new approach to Transfer Learning (TL) in Re...
04/30/2023

Joint Learning of Policy with Unknown Temporal Constraints for Safe Reinforcement Learning

In many real-world applications, safety constraints for reinforcement le...
10/14/2018

Theoretical Guarantees of Transfer Learning

Transfer learning has been proven effective when within-target labeled d...
03/29/2020

Experience Selection Using Dynamics Similarity for Efficient Multi-Source Transfer Learning Between Robots

In the robotics literature, different knowledge transfer approaches have...
11/03/2020

Online Observer-Based Inverse Reinforcement Learning

In this paper, a novel approach to the output-feedback inverse reinforce...
03/13/2018

Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies

In this work, we provide theoretical guarantees for reward decomposition...