Reinforcement Learning for Low Probability High Impact Risks
We demonstrate a method of reinforcement learning that uses training in simulation. Our system generates an estimate of the potential reward and danger of each action as well as a measure of the uncertainty present in both. The system generates this by seeking out not only rewarding actions but also...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2019
|
| Online Access: | http://hdl.handle.net/20.500.11937/77106 |