BROWSE
Detail
Conference Paper
Conservative Reward-Action Balancing Transformer
Cited 0 time in 
Share 
Share
- Authors
- Seonghyun Kim, Samyeul Noh, Ingook Jang
- Issue Date
- 2024-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2024, pp.211-214
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Research in goal-conditioned reinforcement learning (GCRL) aims to deploy trained agents in realistic settings. Offline reinforcement learning has gained attention as a method to minimize the costs associated with online interactions in GCRL. One approach, the Decision Transformer (DT), leverages a numerical target known as 'return-to-go' to achieve enhanced performance. However, because DT assumes an ideal environment with complete knowledge of rewards, there is a need to develop improved techniques for real-world scenarios. This study explores various strategies and outcomes for conservative reward-action balancing transformers designed to function effectively under practical conditions.
- KSP Keywords
- Enhanced performance, Real-world, Reinforcement learning(RL), online interactions