Показати скорочений опис матеріалу
dc.contributor.author | Nahirnyi, Oleksii![]() |
|
dc.date.accessioned | 2022-07-22T10:01:28Z | |
dc.date.available | 2022-07-22T10:01:28Z | |
dc.date.issued | 2022 | |
dc.identifier.citation | Nahirnyi, Oleksii. Reinforcement Learning Agents in Procedurally-generated Environments with Sparse Rewards / Oleksii Nahirnyi; Supervisor: Dr. Pablo Maldonado; Ukrainian Catholic University, Faculty of Applied Sciences, Department of Computer Sciences. – Lviv 2022. – 45 p. | uk |
dc.identifier.uri | https://er.ucu.edu.ua/handle/1/3165 | |
dc.description.abstract | Solving sparse-reward environments is one of the most considerable challenges for state-of-the-art (SOTA) Reinforcement Learning (RL). Recent usage of sparse-rewards in procedurally-generated environments (PGE) to more adequately measure agent’s generalization capabilities via randomization makes this challenge even harder. Despite some progress of newly created exploration-based algorithms in MiniGrid PGEs, the task remains open for research in terms of improving sample complexity. We contribute to solving this task by creating a new formulation of exploratory intrinsic reward. We base this formulation on a thorough review and categorization of other methods in this area. Agent that optimizes an RL objective with such a formulation performs better than SOTA methods in some small or medium sized PGEs. | uk |
dc.language.iso | en | uk |
dc.subject | reinforcement learning | uk |
dc.subject | exploration | uk |
dc.subject | sparse rewards | uk |
dc.subject | procedurally-generated environment | uk |
dc.subject | intrinsic reward | uk |
dc.title | Reinforcement Learning Agents in Procedurally-generated Environments with Sparse Rewards | uk |
dc.type | Preprint | uk |
dc.status | Публікується вперше | uk |