Parameterized modular inverse reinforcement learning
| dc.contributor.advisor | Ballard, Dana H. (Dana Harry), 1946- | |
| dc.contributor.committeeMember | Stone, Peter H | |
| dc.creator | Zhang, Shun, 1990- | |
| dc.creator.orcid | 0000-0002-8073-3276 | |
| dc.date.accessioned | 2017-05-24T19:48:07Z | |
| dc.date.available | 2017-05-24T19:48:07Z | |
| dc.date.issued | 2015-08 | |
| dc.date.submitted | August 2015 | |
| dc.date.updated | 2017-05-24T19:48:07Z | |
| dc.description.abstract | Reinforcement learning and inverse reinforcement learning can be used to model and understand human behaviors. However, due to the curse of dimensionality, their use as a model for human behavior has been limited. Inspired by observed natural behaviors, one approach is to decompose complex tasks into independent sub-tasks, or modules. Using this approach, we extended earlier work on modular inverse reinforcement learning, and developed what we called a parameterized modular inverse reinforcement learning algorithm. We first demonstrate the correctness and efficiency of our algorithm in a simulated navigation task. We then show that our algorithm is able to estimate a reward function and discount factor for real human navigation behaviors in a virtual environment, and train an agent that imitates the behavior of human subjects. | |
| dc.description.department | Computer Science | |
| dc.format.mimetype | application/pdf | |
| dc.identifier | doi:10.15781/T2WD3Q675 | |
| dc.identifier.uri | http://hdl.handle.net/2152/46987 | |
| dc.subject | Reinforcement learning | |
| dc.subject | Artificial intelligence | |
| dc.subject | Inverse reinforcement learning | |
| dc.subject | Modular inverse reinforcement learning | |
| dc.subject | Reinforcement learning algorithms | |
| dc.subject | Human navigation behaviors | |
| dc.title | Parameterized modular inverse reinforcement learning | |
| dc.type | Thesis | |
| dc.type.material | text | |
| thesis.degree.department | Computer Sciences | |
| thesis.degree.discipline | Computer Science | |
| thesis.degree.grantor | The University of Texas at Austin | |
| thesis.degree.level | Masters | |
| thesis.degree.name | Master of Science in Computer Sciences |