New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[FEAT] 강화학습 환경 구현 #1

Open

kuun1000 opened this issue Aug 19, 2024 · 0 comments

Owner

kuun1000 commented Aug 19, 2024

구현할 기능

Observation Space 및 Action Space 정의
Step 함수에서 Action 적용
Q Network 구조 변경
Reward 계산 변경

상세 작업 내용

Observation Space: 자료 조사 필요
Action Space: Discrete
Q Network: RGB image, Depth image, Joint Position 각각 처리
DDQN 알고리즘 반영되었는지 확인 필요

참고 사항

Gripper action: 0(닫힘) 또는 1(열림)
각 Joint 90도 회전하는데 2.5sec 소요됨

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment