Automated Curriculum Learning by Rewarding Temporally Rare Events

Niels Justesen, Sebastian Risi

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstrakt

Reward shaping allows reinforcement learning (RL) agents to accelerate learning by receiving additional reward signals. However, these signals can be difficult to design manually, especially for complex RL tasks. We propose a simple and general approach that determines the reward of pre-defined events by their rarity alone. Here events become less rewarding as they are experienced more often, which encourages the agent to continually explore new types of events as it learns. The adaptiveness of this reward function results in a form of automated curriculum learning that does not have to be specified by the experimenter. We demonstrate that this Rarity of Events (RoE) approach enables the agent to succeed in challenging VizDoom scenarios without access to the extrinsic reward from the environment. Furthermore, the results demonstrate that RoE learns a more versatile policy that adapts well to critical changes in the environment. Rewarding events based on their rarity could help in many unsolved RL environments that are characterized by sparse extrinsic rewards but a plethora of known event types.
OriginalsprogEngelsk
Titel2018 IEEE Conference on Computational Intelligence and Games
Antal sider8
ForlagIEEE
Publikationsdato2018
Sider293-300
ISBN (Trykt)978-1-5386-4359-4
ISBN (Elektronisk)978-1-5386-4359-0
StatusUdgivet - 2018

Fingeraftryk

Dyk ned i forskningsemnerne om 'Automated Curriculum Learning by Rewarding Temporally Rare Events'. Sammen danner de et unikt fingeraftryk.

Citationsformater