Combining Multi-Objective Planning with Reinforcement Learning to Solve Complex Tasks in Environments with Sparse Rewards

Combining Multi-Objective Planning with Reinforcement Learning to Solve Complex Tasks in Environments with Sparse Rewards

van Rijn, Cas (TU Delft Electrical Engineering, Mathematics and Computer Science)

Lukina, A. (mentor)
Spaan, M.T.J. (graduation committee)
Oliehoek, F.A. (graduation committee)

Delft University of Technology

Electrical Engineering | Embedded Systems

2023-03-21

Sequential decision-making problems are problems where the goal is to find a sequence of actions that complete a task in an environment. A particularly difficult type of sequential decision-making problem to solve is one in which the environment has sparse rewards, a large state space, and where the goal is to complete a complex task. In this research we create a controller that can be used to solve these types of environments in cases where the task needs to be optimized for multiple objectives. We create MOPRL, an approach that combines techniques from planning, formal methods, and reinforcement learning to synthesize such a controller. W

Sequential decision making
Reinforcement learning
Planning
LTL tasks
Sparse rewards

http://resolver.tudelft.nl/uuid:1b0a4da5-d239-433b-b428-c927049e9055

Student theses

master thesis

© 2023 Cas van Rijn