Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents
Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is a key component of how humans understand, reason, and act in these worlds. However, it remains unclear to what extent artificial agents utilize semantic understanding of the text. To this end, we perform experiments to systematically reduce the amount of semantic information available to a learning agent. Surprisingly, we find that an agent is capable of achieving high scores even in the complete absence of language semantics, indicating that the currently popular experimental setup and models may be poorly designed to understand and leverage game texts. To remedy this deficiency, we propose an inverse dynamics decoder to regularize the representation space and encourage exploration, which shows improved performance on several games including Zork I. We discuss the implications of our findings for designing future agents with stronger semantic understanding.
Code (0)
등록된 구현이 없습니다.
Tasks
Decodertext-based gamesSimilar Papers 제목 키워드 기반
Blindfolded Spider-man Optimization: A Single-Point Metaheuristics Suitable for Continuous and Discrete Spaces
In this study, we introduce a new single point metaheuristic optimization approach suitable for both continuous and discrete domains. The proposed algorithm, entitled Blindfolded Spiderman Optimization, follows a piecewi…
Metaheuristic OptimizationBlindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
Behavioral cloning is a simple yet effective technique for learning sequential decision-making from demonstrations. Recently, it has gained prominence as the core of foundation models for the physical world, where achiev…
TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
Since real-world ubiquitous documents (e.g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic. Most existing works decouple the problem into…
document understandingText Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Modern text-to-image diffusion transformers (DiTs) generate images through joint attention, in which text and image tokens interact directly within a single sequence. In large-scale DiTs, the conditioning input contains …
E3: Entailment-driven Extracting and Editing for Conversational Machine Reading
Conversational machine reading systems help users answer high-level questions (e.g. determine if they qualify for particular government benefits) when they do not know the exact rules by which the determination is made(e…
Reading Comprehension