Joint Action Language Modelling for Transparent Policy Execution
An agent's intention often remains hidden behind the black-box nature of embodied policies. Communication using natural language statements that describe the next action can provide transparency towards the agent's behavior. We aim to insert transparent behavior directly into the learning process, by transforming the problem of policy learning into a language generation problem and combining it with traditional autoregressive modelling. The resulting model produces transparent natural language statements followed by tokens representing the specific actions to solve long-horizon tasks in the Language-Table environment. Following previous work, the model is able to learn to produce a policy represented by special discretized tokens in an autoregressive manner. We place special emphasis on investigating the relationship between predicting actions and producing high-quality language for a transparent agent. We find that in many cases both the quality of the action trajectory and the transparent statement increase when they are generated simultaneously.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModellingText GenerationSimilar Papers 제목 키워드 기반
Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions
The moderation of content on online platforms is usually non-transparent. On Wikipedia, however, this discussion is carried out publicly and the editors are encouraged to use the content moderation policies as explanatio…
Decision MakingStance DetectionA Formally Grounded ODRL Evaluator: Implementation and Comparison
The ODRL policy language is emerging as the de-facto standard for policy modelling data access and usage preferences, AI governance policies and data workflows in European dataspaces. The current standard has no mathemat…
JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning
Dialogue policy learning (DPL) is a crucial component of dialogue modelling. Its primary role is to determine the appropriate abstract response, commonly referred to as the "dialogue action". Traditional DPL methodologie…
Action GenerationDiversityJointly modelling the evolution of social structure and language in online communities
Group interactions take place within a particular socio-temporal context, which should be taken into account when modelling interactions in online communities. We propose a method for jointly modelling community structur…
Word EmbeddingsNo such thing as a risk-neutral market
A very brief history of relative valuation in neoclassical finance since 1973 is presented, with attention to core currency issues for emerging economies. Price formation is considered in the context of hierarchical caus…