Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals
원문 초록
High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-performing agent. We propose the Read and Reward framework. Read and Reward speeds up RL algorithms on Atari games by reading manuals released by the Atari game developers. Our framework consists of a QA Extraction module that extracts and summarizes relevant information from the manual and a Reasoning module that evaluates object-agent interactions based on information from the manual. An auxiliary reward is then provided to a standard A2C RL agent, when interaction is detected. Experimentally, various RL algorithms obtain significant improvement in performance and training speed when assisted by our design.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Meta-learning how to Share Credit among Macro-Actions
TextAtari: 100K Frames Game Playing with Language Agents
Unraveling the Rainbow: can value-based methods schedule?
Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents
토론
이 논문과 연결된 포럼 글이 아직 없습니다.