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 |
| _version_ | 1848763816724135936 |
|---|---|
| author | Hunt, Gareth David |
| author_facet | Hunt, Gareth David |
| author_sort | Hunt, Gareth David |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | 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 dangerous ones in the simulated training. During runtime our system is able to use this knowledge to avoid risks while accomplishing its tasks. |
| first_indexed | 2025-11-14T11:09:29Z |
| format | Thesis |
| id | curtin-20.500.11937-77106 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:09:29Z |
| publishDate | 2019 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-771062019-12-05T05:25:12Z Reinforcement Learning for Low Probability High Impact Risks Hunt, Gareth David 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 dangerous ones in the simulated training. During runtime our system is able to use this knowledge to avoid risks while accomplishing its tasks. 2019 Thesis http://hdl.handle.net/20.500.11937/77106 Curtin University fulltext |
| spellingShingle | Hunt, Gareth David Reinforcement Learning for Low Probability High Impact Risks |
| title | Reinforcement Learning for Low Probability High Impact Risks |
| title_full | Reinforcement Learning for Low Probability High Impact Risks |
| title_fullStr | Reinforcement Learning for Low Probability High Impact Risks |
| title_full_unstemmed | Reinforcement Learning for Low Probability High Impact Risks |
| title_short | Reinforcement Learning for Low Probability High Impact Risks |
| title_sort | reinforcement learning for low probability high impact risks |
| url | http://hdl.handle.net/20.500.11937/77106 |