Natural Language-conditioned reinforcement learning (RL) enables the agents to follow human instructions. Previous approaches generally implemented language-conditioned RL by providing human instructions in natural language (NL) and training a following policy. In this outside-in approach, the policy needs to comprehend the NL and manage the task simultaneously. However, the unbounded NL examples often bring much extra complexity for solving concrete RL tasks, which can distract policy learning from completing the task. To ease the learning burden of the policy, we investigate an inside-out scheme for natural language-conditioned RL by developing a task language (TL) that is task-related and unique. The TL is used in RL to achieve highly efficient and effective policy training. Besides, a translator is trained to translate NL into TL. We implement this scheme as TALAR (TAsk Language with predicAte Representation) that learns multiple predicates to model object relationships as the TL. Experiments indicate that TALAR not only better comprehends NL instructions but also leads to a better instruction-following policy that improves 13.4% success rate and adapts to unseen expressions of NL instruction. The TL can also be an effective task abstraction, naturally compatible with hierarchical RL.
ProMORNA: An End-to-End Generative Framework for Full-Length mRNA Design
Nanjing Foreign Language School（南京外国语学校）；School of Science, China Pharmaceutical University（中国药科大学理学院）；School of Pharmacy, China Pharmaceutical University（中国药科大学药学院）
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS)（里约格兰德杜斯阿伦斯天主教大学）；Universidade do Vale do Rio dos Sinos (Unisinos)（里约斯inos大学）；University of Aberdeen（阿伯丁大学）
NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL
Huazhong University of Science and Technology（华中科技大学）；Xi’an Jiaotong University（西安交通大学）；University of Electronic Science and Technology of China（电子科技大学）
Low Resource Multimodal Translation of Nepali Spoken Words into Emotion-Conditioned Sign Language Avatars
Center for Human Mobility and Communications, Prateek Innovations（普拉蒂克创新公司人类移动与通信中心）；Sunway International Business School, Birmingham City University（双威国际商学院，伯明翰城市大学）
Conditioned in Training, Dispensable at Inference: Typological Conditioning for Multilingual Speech Translation
School of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电子工程学院）；Recho Inc.（Recho公司）；National Institute of Informatics（国家信息研究所）；Interdisciplinary Research Centre on Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学安全、可靠性与信任跨学科研究中心）；Donghua University（东华大学）；Department of Computer Science, The University of Tokyo（东京大学计算机科学系）；Department of Electrical and Computer Engineering, University of Alberta（阿尔伯塔大学电子与计算机工程系）
Bridging the Gap between Training and Inference for Neural Machine Translation
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent Inc（腾讯公司）；Worcester Polytechnic Institute（伍斯特理工学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation
Alibaba DAMO Academy（阿里巴巴达摩院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
