Mental Modeling Of Reinforcement Learning Agents By Language Models
2024 · Wenhao Lu, Xufeng Zhao, Josua Spisak, et al.
Abstract
Can emergent language models faithfully model the intelligence of decision-making agents? Though modern language models exhibit already some reasoning ability, and theoretically can potentially express any probable distribution over tokens, it remains underexplored how the world knowledge these pretrained models have memorized can be utilized to comprehend an agent's behaviour in the physical world. This study empirically examines, for the first time, how well large language models (LLMs) can build a mental model of agents, termed agent mental modelling, by reasoning about an agent's behaviour and its effect on states from agent interaction history. This research may unveil the potential of leveraging LLMs for elucidating RL agent behaviour, addressing a key challenge in eXplainable reinforcement learning (XRL). To this end, we propose specific evaluation metrics and test them on selected RL task datasets of varying complexity, reporting findings on agent mental model establishment. Ou
Authors
(none)
Tags
Stats
Related papers
- Talktoagent: A Human-centric Explanation Of Reinforcement Learning Agents With Large Language Models (2025)0.00
- Language Agents With Reinforcement Learning For Strategic Play In The Werewolf Game (2023)0.00
- Think In Games: Learning To Reason In Games Via Reinforcement Learning With Large Language Models (2025)0.00
- From Laws To Motivation: Guiding Exploration Through Law-based Reasoning And Rewards (2024)0.00
- Language-driven Coordination And Learning In Multi-agent Simulation Environments (2025)0.00
- Multi-agent Reinforcement Learning As A Computational Tool For Language Evolution Research: Historical Context And Future Challenges (2020)0.00
- MAGE: Meta-reinforcement Learning For Language Agents Toward Strategic Exploration And Exploitation (2026)0.00
- DLM: Unified Decision Language Models For Offline Multi-agent Sequential Decision Making (2026)0.00