Abstract
In traditional reinforcement learning (RL) problems, agents can explore environments to learn optimal policies through trials and errors that are sometimes unsafe. However, unsafe interactions with environments are unacceptable in many safety-critical problems, for instance in robot navigation tasks. Even though RL agents can be trained in simulators, there are many real-world problems without simulators of sufficient fidelity. Constructing safe exploration algorithms for dangerous environments is challenging because we have to optimize policies under the premise of safety. In general, safety is still an open problem that hinders the wider application of RL.
Original language | English |
---|---|
Qualification | Doctor of Philosophy |
Awarding Institution |
|
Supervisors/Advisors |
|
Award date | 23 Jun 2023 |
Electronic ISBNs | 978-94-6384-458-1 |
DOIs | |
Publication status | Published - 2023 |
Keywords
- Reinforcement Leaning (RL)
- constrained optimization
- quantile regression
- taskagnostic exploration