Value Memory Graph: A Graph-Structured word model for offline reinforcement learning

Editor: ๋ฏผ์˜ˆ๋ฆฐ (Yerin Min) arXiv Github

1. Introduction

  • ์‚ฌ๋žŒ์ด ์˜์‚ฌ ๊ฒฐ์ •์„ ํ•  ๋•Œ๋Š” ์ผ๋ฐ˜์ ์œผ๋กœ ์‚ฌ์†Œํ•œ ์ •๋ณด๋Š” ๋ฌด์‹œํ•˜๊ณ  ์ค‘์š”ํ•œ ์ •๋ณด์— ๋” ์ง‘์ค‘ํ•จ์œผ๋กœ์จ ์–ด๋ ค์šด ๋ฌธ์ œ๋ฅผ ๋‹จ์ˆœํ™”ํ•จ.

Last updated