Georgia Southern University
Reinforcement Learning: Applying Low Discrepancy Action Selection to Deep Deterministic Policy Gradient
Abstract
dc:description.abstractReinforcement learning (RL) is a subfield of machine learning concerned with agents learning to behave optimally by interacting with an environment. One of the most important topics in RL is how the agent should explore, that is, how to choose actions in order to rate their impact on long-term reward. For example, a simple baseline strategy might be uniformly random action selection. This thesis investigates the heuristic idea that agents will learn faster if they explore by factoring the environment’s state into their decision and intentionally choose actions which are as different as possible from what they have previously observed. Experiments are run to discover whether this algorithm is computationally reasonable, and whether the agent learns significantly faster compared to baseline exploration strategies.
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Mathematics (M.S.)
- Level thesis:degree_level
- Thesis (open access)
- Discipline thesis:degree_discipline
- Department of Mathematical Sciences
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Svishchev, Aleksandr
- Contributors dc:contributor
-
- Ionut Iacob
- Zheni Utic
Subjects
dc:subject × 6Rights
- Licence dc:rights.license
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.georgiasouthern.edu/etd/2707