Reinforcement learning in the presence of rare events
Learning agents often find themselves in environments in which rare significant events occur independently of their current choice of action. Traditional reinforcement learning algorithms sample events according to their natural probability of occurring, and therefore tend to exhibit slow convergenc...
| Main Author: | |
|---|---|
| Format: | Others |
| Language: | en |
| Published: |
McGill University
2009
|
| Subjects: | |
| Online Access: | http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=111576 |