Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-task Reinforcement Learning on DmLab-30 (train)

0.735Mean capped human normalised score

PopArt-IMPALA

0.600840.635670.67050.70533Sep 12, 2018
Updated 1mo ago

Evaluation Results

MethodLinks
2018.09
0.735
2018.09
0.606