DeepAI AI Chat
Log In Sign Up

Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks

by   C. Drummond, et al.

This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The system achieves much of its power by transferring parts of previously learned solutions rather than a single complete solution. The system exploits strong features in the multi-dimensional function produced by reinforcement learning in solving a particular task. These features are stable and easy to recognize early in the learning process. They generate a partitioning of the state space and thus the function. The partition is represented as a graph. This is used to index and compose functions stored in a case base to form a close approximation to the solution of the new task. Experiments demonstrate that function composition often produces more than an order of magnitude increase in learning rate compared to a basic reinforcement learning algorithm.


page 1

page 2

page 3

page 4


Reinforcement Learning for the Soccer Dribbling Task

We propose a reinforcement learning solution to the soccer dribbling tas...

Transfer of Temporal Logic Formulas in Reinforcement Learning

Transferring high-level knowledge from a source task to a target task is...

Tutoring Reinforcement Learning via Feedback Control

We introduce a control-tutored reinforcement learning (CTRL) algorithm. ...

On Reinforcement Learning for Full-length Game of StarCraft

StarCraft II poses a grand challenge for reinforcement learning. The mai...

A new Potential-Based Reward Shaping for Reinforcement Learning Agent

Potential-based reward shaping (PBRS) is a particular category of machin...

Approximating Energy Market Clearing and Bidding With Model-Based Reinforcement Learning

Energy markets can provide incentives for undesired behavior of market p...

Learning to Transfer: A Foliated Theory

Learning to transfer considers learning solutions to tasks in a such way...