Skip to content

1 min

Align-RUDDER: learning from few demonstrations by reward redistribution

Replacing RUDDER's LSTM with a profile model from multiple sequence alignment, so reward redistribution works from a handful of demonstrations.

First published on dinu.at. Ported here with its figures.

Abstract

Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage steps in the Q-function that are associated with accomplishing sub-tasks. However, often only few episodes with high rewards are available as demonstrations since current exploration strategies cannot discover them in reasonable time. In this work, we introduce Align-RUDDER, which utilizes a profile model for reward redistribution that is obtained from multiple sequence alignment of demonstrations. Consequently, Align-RUDDER employs reward redistribution effectively and, thereby, drastically improves learning on few demonstrations. Align-RUDDER outperforms competitors on complex artificial tasks with delayed rewards and few demonstrations. On the Minecraft ObtainDiamond task, Align-RUDDER is able to mine a diamond, though not frequently. Code is available at github.com/ml-jku/align-rudder.

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution — watch on YouTube

The paper is on arXiv.

← All writing