How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds
원문 초록
Text-based games are long puzzles or quests, characterized by a sequence of sparse and potentially deceptive rewards. They provide an ideal platform to develop agents that perceive and act upon the world using a combinatorially sized natural language state-action space. Standard Reinforcement Learning agents are poorly equipped to effectively explore such spaces and often struggle to overcome bottlenecks---states that agents are unable to pass through simply because they do not see the right action sequence enough times to be sufficiently reinforced. We introduce Q*BERT, an agent that learns to build a knowledge graph of the world by answering questions, which leads to greater sample efficiency. To overcome bottlenecks, we further introduce MC!Q*BERT an agent that uses an knowledge-graph-based intrinsic motivation to detect bottlenecks and a novel exploration strategy to efficiently learn a chain of policy modules to overcome them. We present an ablation study and results demonstrating how our method outperforms the current state-of-the-art on nine text games, including the popular game, Zork, where, for the first time, a learning agent gets past the bottleneck where the player is eaten by a Grue.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
TextArena
Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games
TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning
STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.