Augmented-Ensemble TD3 : Overcoming the Shackles of Constant Action Delay
- Title
- Augmented-Ensemble TD3 : Overcoming the Shackles of Constant Action Delay
- Authors
- Jongsoo Lee; HAN, SOOHEE
- Date Issued
- 2023-10-18
- Publisher
- KROS, IEEE
- Abstract
- Reinforcement Learning has experienced significant advances in various domains. However, delayed feedback
in RL environments poses challenges due to the violation of the Markovian property. In this paper, we propose
an approach to address the issues of Markov Decision Process(MDP) with delayed feedback. The proposed approach,
called ”Augmented-Ensemble Twin-Delayed Deep Deterministic Policy Gradient(TD3),” aims to mitigate the performance
degradation caused by delayed feedback.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/122412
- Article Type
- Conference
- Citation
- 2023 The 23rd International Conference on Control, Automation and Systems (ICCAS 2023), 2023-10-18
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.