Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 30편

Unsupervised Reinforcement Learning Benchmark

URLB
URLB 설명 보기

URLB consists of two phases: reward-free pre-training and downstream task adaptation with extrinsic rewards. Building on the DeepMind Control Suite, it provides twelve continuous control tasks from three domains for evaluation.