Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning
We investigate the use of natural language to drive the generalization of policies in multi-agent settings. Unlike single-agent settings, the generalization of policies should also consider the influence of other agents. Besides, with the increasing number of entities in multi-agent settings, more agent-entity interactions are needed for language grounding, and the enormous search space could impede the learning process. Moreover, given a simple general instruction,e.g., beating all enemies, agents are required to decompose it into multiple subgoals and figure out the right one to focus on. Inspired by previous work, we try to address these issues at the entity level and propose a novel framework for language grounding in multi-agent reinforcement learning, entity divider (EnDi). EnDi enables agents to independently learn subgoal division at the entity level and act in the environment based on the associated entities. The subgoal division is regularized by opponent modeling to avoid subgoal conflicts and promote coordinated strategies. Empirically, EnDi demonstrates the strong generalization ability to unseen games with new dynamics and expresses the superiority over existing methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms
As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to decide whether to trust an unfamiliar agent in the wild and delegate …
Adversarial AttackFair Division with Money and Prices
We must divide a finite number of indivisible goods and cash transfers between agents with quasi-linear but otherwise arbitrary utilities over the subsets of goods. We compare two division rules with cognitively feasible…
Privacy PreservingDesign of a compact low loss 2-way millimetre wave power divider for future communication
In this paper, a rectangular-shaped power divider has been presented operating at 27.9 GHz. The power divider has achieved acceptable results for important parameters such as S11, S12, S21, and S22. The substrate employe…
ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models
Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining insensitive to instruction changes. We present Prospective Grounding an…
A-PAIR: A Benchmark and Identity-Consistent Grounding Framework for Air-Ground Cross-View Referring Person Detection
Air-ground cross-view referring person detection is a necessary component in the language-to-perception-to-control chain of collective embodied intelligence, grounding a language command into the same physical target bef…
Referring Expression