Can I read Meta-Reinforcement Learning for Heuristic Planning on EtoBox?

Meta-Reinforcement Learning for Heuristic Planning by Gutierrez, Ricardo Luna; Leonetti, Matteo is a scholarly article available to read on EtoBox.

What is Meta-Reinforcement Learning for Heuristic Planning about?

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually hand-crafted to be representative of the expected distribution of test tasks and hence all used in training. We show that given a set of training tasks, learning can be both faster and more effective (leading to better performance in the test tasks), if the training tasks are appropriately selected. We propose a task selection algorithm, Information-Theoretic Task Selection (ITTS), based on information theory, which optimizes the set of tasks used for training in meta-RL, irrespectively of how they are generated. The algorithm establishes which training tasks are both sufficiently relevant for the test tasks, and different enough from one another. We reproduce different meta-RL experiments from the literature and show that ITTS improves the final performance in all of them.

Author

Gutierrez, Ricardo Luna; Leonetti, Matteo

Published

2021

Language

EN