Learning hierarchical control structures for multiple tasks and changing environments
Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
A Heuristic Approach to the Discovery of Macro-Operators
Machine Learning
Composing Functions to Speed up Reinforcement Learning in a Changing World
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Hi-index | 0.00 |
This paper presents a new method by which a sequential decision agent can automatically discover subgoals online. The agent discovers subgoals using potential field. The method uses a reward function to generate a potential field, and then abstracts some features from the potential field as candidates of subgoals. Based on the candidates, the agent can determine its behaviors online through some heuristics in unknown environment. The best-known and most often-cited problem with the potential field method is local minima. But our method does not have this limitation because the local minima are used to form subgoals. The disadvantage of the local minima in the previous approaches of potential field turns out to be an advantage in our method. We illustrate the method using a simple gridworld task.