Learning State Abstractions for Transfer in Continuous Control
Asadi, Kavosh, Abel, David, Littman, Michael L.
–arXiv.org Artificial Intelligence
Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be continuous control tasks. Our main contribution is a learning algorithm that abstracts a continuous state-space into a discrete one. We transfer this learned representation to unseen problems to enable effective learning. We provide theory showing that learned abstractions maintain a bounded value loss, and we report experiments showing that the abstractions empower tabular Q-Learning to learn efficiently in unseen tasks.
arXiv.org Artificial Intelligence
Feb-8-2020
- Country:
- North America > United States
- Texas > Travis County > Austin (0.04)
- Europe > United Kingdom
- England (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report (0.83)
- Industry:
- Leisure & Entertainment > Games (0.68)
- Education (0.66)
- Technology: