【EAI 019】Eureka: Human-Level Reward Design via Coding LLM
论文标题:Eureka:Human-LevelRewardDesignviaCodingLargeLanguageModels论文作者:YechengJasonMa,WilliamLiang,GuanzhiWang,De-AnHuang,OsbertBastani,DineshJayaraman,YukeZhu,LinxiFan,AnimaAnandkumar作者单位:NVIDIA;UPenn;C