Inferring Rewards from Language in Context
원문 초록
In classic instruction following, language like "I'd like the JetBlue flight" maps to actions (e.g., selecting that flight). However, language also conveys information about a user's underlying reward function (e.g., a general preference for JetBlue), which can allow a model to carry out desirable actions in new contexts. We present a model that infers rewards from language pragmatically: reasoning about how speakers choose utterances not only to elicit desired actions, but also to reveal information about their preferences. On a new interactive flight-booking task with natural language, our model more accurately infers rewards and predicts optimal actions in unseen environments, in comparison to past work that first maps language to actions (instruction following) and then maps actions to rewards (inverse reinforcement learning).
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Kwai Keye-VL Technical Report
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval
Magistral
On the Mechanism of Reasoning Pattern Selection in Reinforcement Learning for Language Models
High-Throughput Distributed Reinforcement Learning via Adaptive Policy Synchronization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.